TOP ACTIVATIONS
MAX = 8.803

12 . Donkey Kong Country 2 : D iddy
in Japan if everyone comes out and has a great time
p . m .: The number of injured has reached 132
11 . The Legend of Zelda : O car ina of
K people are still coming out with shorts from this site
the first step in a sweeping review of the tobacco industry
not heard of the Republican strategist despite his having been widely
grapp ler in the Street Fighter series to ever have a
poll conducted this weekend in Wisconsin , another state with a
, paid for by George Soros 's pre - tax dollars
. Fro do falls to Shel ob 's sting . But
Before the gameplay proved Donkey Kong Country 2 : D iddy
release date for " Final Fantasy V X " will be
9 million in April , narrowly in ching out Mrs .
risk of the situation in Chennai becoming even worse over the
to Recap San Juan Del Sur Episode 5 Coach
details and analysis . <|endoftext|> Sym one Sanders was not having
at town meetings in New Hampshire and Iowa are sending a
com By the numbers 12 , 000
we ll come out on top .

MIN ACTIVATIONS
MIN = -8.355

her personal story as supporting evidence . Sim pl
org / index . php ? topic = 28 18 48
/ acs 5 / profile ? get = NAME , DP
were part of the messages Ms . Lerner lost in a
Sen . Cruz was no exception , a Cruz
our eyebrows and blew our minds in 2014 . Buck le
. It was just one example of Trump attempting to mend
appeal to remain somewhat un spoken ? Part of
air spe eds . Un spoken , but understood , was
The added Game Pad features elicit the same You
word " custom ize " disappear ... until I closed and
outgoing and is a good conversation starter . <|endoftext|> Well ,
is just one of many instances of legal American citizens being
being seen as the latest instance of a new mood of
com / iv xx brand ? f ref = ts <|endoftext|>
access to calendars . One cabinet pick stands out , however
to discover the most used Clojure testing library . The answer
youtube . com / watch ? v = 2 g 7
category , where Emmy - neg lected The Good Wife was
complaint against the club on Oct . 9 , 2015 .

INTERVAL 4.514 - 8.803
CONTAINS 0.257%

education they can and then use it to ' lead by
.[ 158 ] See also [ edit ] <|endoftext|>
northwest corner of St . Clair and Avenue Road
rooting for the Democratic presidential candidate say their accounts on the
handle multiple spikes in the angle - of - attack data

INTERVAL 0.224 - 4.514
CONTAINS 43.172%

be 09 c 68 a 410 f 6 bed 15 c
. However , now the tide has turned again
? What is it ? I ll definitely grant
arrive in an hour or two . The outside is becoming
" For all the pomp and ceremony , nothing in

INTERVAL -4.065 - 0.224
CONTAINS 56.007%

car ibe deal would help lower and stabilize the cost of
by trying to reconcile that with his religion , culture ,
a very interesting session to say the least . I consider
Committee . F ess end en took no immediate action ,
. Impro ving delivery of services to the stakeholders

INTERVAL -8.355 - -4.065
CONTAINS 0.564%

t one of the bureau s many tech
this all happens from Monday April 30 th at 1900 g
able to prevent the Petro car ibe deal for two years
executions took place on Sunday November 3 , a source told
of his ret raction and silence . This year , on
Token
Token ID198
Feature activation+1.41e+00

Pos logit contributions
LLOW+0.469
tten+0.453
��+0.442
 Swordsman+0.437
FACE+0.430
Neg logit contributions
ippers-0.433
ipper-0.423
rones-0.337
lems-0.336
ploy-0.329
Token
Token ID198
Feature activation+9.07e-01

Pos logit contributions
LLOW+1.097
tten+1.062
��+1.015
 Swordsman+1.007
FACE+1.006
Neg logit contributions
ippers-1.025
ipper-0.998
rones-0.796
lems-0.788
lihood-0.788
Token12
Token ID1065
Feature activation+2.70e-01

Pos logit contributions
LLOW+0.581
tten+0.561
��+0.545
FACE+0.525
 Swordsman+0.521
Neg logit contributions
ippers-0.788
ipper-0.772
rones-0.640
lihood-0.637
lems-0.637
Token.
Token ID13
Feature activation-3.70e-01

Pos logit contributions
LLOW+0.198
tten+0.192
��+0.186
 Swordsman+0.182
FACE+0.180
Neg logit contributions
ippers-0.210
ipper-0.205
rones-0.166
lems-0.165
 Carney-0.163
Token Donkey
Token ID43823
Feature activation+5.10e+00

Pos logit contributions
ippers+0.293
ipper+0.287
rones+0.233
lems+0.233
 Carney+0.230
Neg logit contributions
LLOW-0.266
tten-0.259
��-0.253
 Swordsman-0.245
FACE-0.241
Token Kong
Token ID9071
Feature activation+8.80e+00

Pos logit contributions
LLOW+1.295
tten+1.110
��+1.058
FACE+1.042
 Swordsman+1.016
Neg logit contributions
ippers-6.266
ipper-6.148
lems-5.563
lihood-5.526
rones-5.511
Token Country
Token ID12946
Feature activation+4.44e+00

Pos logit contributions
LLOW+4.867
tten+4.641
 Swordsman+4.473
ADRA+4.230
��+4.219
Neg logit contributions
ippers-7.830
ipper-7.657
lems-6.602
rones-6.588
lihood-6.500
Token 2
Token ID362
Feature activation+3.01e+00

Pos logit contributions
LLOW+3.068
tten+2.974
��+2.811
 Swordsman+2.786
 Bleach+2.699
Neg logit contributions
ippers-3.570
ipper-3.505
lems-2.896
rones-2.876
lihood-2.864
Token:
Token ID25
Feature activation+3.11e+00

Pos logit contributions
LLOW+2.378
tten+2.320
��+2.248
 Swordsman+2.189
FACE+2.170
Neg logit contributions
ippers-2.161
ipper-2.109
rones-1.676
lems-1.674
 Carney-1.653
Token D
Token ID360
Feature activation+1.19e+00

Pos logit contributions
LLOW+2.147
tten+2.057
 Swordsman+1.983
��+1.972
FACE+1.930
Neg logit contributions
ippers-2.475
ipper-2.441
rones-2.034
mast-1.998
ploy-1.998
Tokeniddy
Token ID34208
Feature activation+4.18e+00

Pos logit contributions
LLOW+0.875
tten+0.853
��+0.831
 Swordsman+0.801
ADRA+0.797
Neg logit contributions
ippers-0.922
ipper-0.902
lems-0.733
rones-0.728
 Carney-0.727
Token in
Token ID287
Feature activation-3.26e-01

Pos logit contributions
ippers+0.234
ipper+0.228
rones+0.187
lems+0.185
 Carney+0.184
Neg logit contributions
LLOW-0.213
tten-0.208
��-0.200
 Swordsman-0.197
FACE-0.193
Token Japan
Token ID2869
Feature activation+1.80e+00

Pos logit contributions
ippers+0.237
ipper+0.231
rones+0.185
lems+0.184
 Carney+0.182
Neg logit contributions
LLOW-0.256
tten-0.249
��-0.244
 Swordsman-0.237
FACE-0.233
Token if
Token ID611
Feature activation+3.14e-02

Pos logit contributions
LLOW+1.266
tten+1.232
��+1.184
 Swordsman+1.163
FACE+1.141
Neg logit contributions
ippers-1.441
ipper-1.410
rones-1.153
lems-1.145
lihood-1.137
Token everyone
Token ID2506
Feature activation+1.76e+00

Pos logit contributions
LLOW+0.028
tten+0.027
��+0.027
 Swordsman+0.026
FACE+0.026
Neg logit contributions
ippers-0.019
ipper-0.019
rones-0.014
lems-0.014
 Carney-0.014
Token comes
Token ID2058
Feature activation+2.58e+00

Pos logit contributions
LLOW+1.373
tten+1.337
��+1.292
 Swordsman+1.268
FACE+1.239
Neg logit contributions
ippers-1.271
ipper-1.249
rones-0.991
lems-0.984
ploy-0.979
Token out
Token ID503
Feature activation+7.75e+00

Pos logit contributions
LLOW+1.789
tten+1.714
��+1.652
 Swordsman+1.622
FACE+1.593
Neg logit contributions
ippers-2.083
ipper-2.041
rones-1.682
lems-1.656
mast-1.653
Token and
Token ID290
Feature activation+1.59e+00

Pos logit contributions
LLOW+4.973
tten+4.835
 Swordsman+4.540
 Bleach+4.511
��+4.449
Neg logit contributions
ippers-6.126
ipper-5.951
rones-5.034
ploy-5.004
lems-4.940
Token has
Token ID468
Feature activation+1.41e+00

Pos logit contributions
LLOW+1.433
tten+1.401
��+1.364
 Swordsman+1.338
FACE+1.323
Neg logit contributions
ippers-0.955
ipper-0.929
rones-0.701
lems-0.694
ploy-0.689
Token a
Token ID257
Feature activation+1.14e+00

Pos logit contributions
LLOW+1.117
tten+1.096
��+1.058
 Swordsman+1.032
FACE+1.025
Neg logit contributions
ippers-1.013
ipper-0.995
rones-0.789
lems-0.782
ploy-0.774
Token great
Token ID1049
Feature activation-1.05e+00

Pos logit contributions
LLOW+0.857
tten+0.838
��+0.815
 Swordsman+0.792
FACE+0.783
Neg logit contributions
ippers-0.862
ipper-0.842
lems-0.678
rones-0.677
 Carney-0.668
Token time
Token ID640
Feature activation-1.93e-03

Pos logit contributions
ippers+0.800
ipper+0.783
rones+0.630
lems+0.627
 Carney+0.623
Neg logit contributions
LLOW-0.787
tten-0.767
��-0.752
 Swordsman-0.725
ADRA-0.719
Token p
Token ID279
Feature activation-1.53e+00

Pos logit contributions
ippers+0.212
ipper+0.207
rones+0.161
lems+0.160
 Carney+0.159
Neg logit contributions
LLOW-0.270
tten-0.264
��-0.259
 Swordsman-0.251
ADRA-0.249
Token.
Token ID13
Feature activation-1.34e+00

Pos logit contributions
ippers+1.129
ipper+1.105
rones+0.882
lems+0.881
 Carney+0.872
Neg logit contributions
LLOW-1.187
tten-1.162
��-1.148
ADRA-1.102
 Swordsman-1.099
Tokenm
Token ID76
Feature activation+7.17e-01

Pos logit contributions
ippers+0.894
ipper+0.871
rones+0.677
lems+0.674
 Carney+0.667
Neg logit contributions
LLOW-1.134
tten-1.108
��-1.089
 Swordsman-1.055
ADRA-1.046
Token.:
Token ID11207
Feature activation+1.79e+00

Pos logit contributions
LLOW+0.444
tten+0.432
��+0.420
 Swordsman+0.403
ADRA+0.398
Neg logit contributions
ippers-0.638
ipper-0.626
rones-0.523
lems-0.522
 Carney-0.518
Token The
Token ID383
Feature activation+1.85e+00

Pos logit contributions
LLOW+1.318
tten+1.254
��+1.229
 Swordsman+1.210
FACE+1.194
Neg logit contributions
ippers-1.409
ipper-1.378
rones-1.112
lems-1.106
lihood-1.090
Token number
Token ID1271
Feature activation+7.55e+00

Pos logit contributions
LLOW+1.421
tten+1.371
��+1.351
 Swordsman+1.306
FACE+1.287
Neg logit contributions
ippers-1.374
ipper-1.339
rones-1.074
lems-1.066
lihood-1.057
Token of
Token ID286
Feature activation+2.78e+00

Pos logit contributions
LLOW+5.265
tten+5.057
��+4.990
FACE+4.764
 Swordsman+4.730
Neg logit contributions
ippers-5.884
ipper-5.780
lems-4.735
rones-4.672
mast-4.612
Token injured
Token ID6686
Feature activation+1.66e+00

Pos logit contributions
LLOW+1.873
tten+1.827
��+1.782
 Swordsman+1.720
FACE+1.699
Neg logit contributions
ippers-2.290
ipper-2.252
rones-1.843
lems-1.830
mast-1.813
Token has
Token ID468
Feature activation+1.57e+00

Pos logit contributions
LLOW+1.337
tten+1.299
��+1.266
 Swordsman+1.243
FACE+1.225
Neg logit contributions
ippers-1.163
ipper-1.144
lems-0.896
rones-0.885
mast-0.876
Token reached
Token ID4251
Feature activation+8.75e-01

Pos logit contributions
LLOW+1.076
tten+1.057
��+1.030
 Swordsman+0.983
FACE+0.976
Neg logit contributions
ippers-1.278
ipper-1.255
lems-1.022
rones-1.022
lihood-1.009
Token 132
Token ID21761
Feature activation+1.23e+00

Pos logit contributions
LLOW+0.634
tten+0.619
��+0.603
 Swordsman+0.584
FACE+0.575
Neg logit contributions
ippers-0.686
ipper-0.672
rones-0.546
lems-0.541
lihood-0.536
Token11
Token ID1157
Feature activation+3.40e-01

Pos logit contributions
LLOW+0.435
tten+0.424
��+0.415
 Swordsman+0.401
FACE+0.398
Neg logit contributions
ippers-0.410
ipper-0.401
rones-0.318
lems-0.318
lihood-0.315
Token.
Token ID13
Feature activation-1.21e+00

Pos logit contributions
LLOW+0.250
tten+0.242
��+0.235
 Swordsman+0.229
FACE+0.227
Neg logit contributions
ippers-0.265
ipper-0.258
rones-0.209
lems-0.208
 Carney-0.206
Token The
Token ID383
Feature activation+5.34e-01

Pos logit contributions
ippers+0.983
ipper+0.963
rones+0.787
lems+0.785
 Carney+0.782
Neg logit contributions
LLOW-0.847
tten-0.826
��-0.810
 Swordsman-0.773
ADRA-0.770
Token Legend
Token ID9883
Feature activation+2.25e+00

Pos logit contributions
LLOW+0.367
tten+0.355
��+0.345
 Swordsman+0.338
FACE+0.329
Neg logit contributions
ippers-0.441
ipper-0.431
rones-0.356
lems-0.353
lihood-0.350
Token of
Token ID286
Feature activation+1.23e+00

Pos logit contributions
LLOW+1.775
tten+1.732
��+1.697
 Swordsman+1.643
ADRA+1.624
Neg logit contributions
ippers-1.627
ipper-1.588
rones-1.263
lems-1.258
 Carney-1.246
Token Zelda
Token ID22166
Feature activation+7.41e+00

Pos logit contributions
LLOW+0.747
tten+0.724
��+0.705
 Swordsman+0.680
ADRA+0.664
Neg logit contributions
ippers-1.102
ipper-1.082
rones-0.904
lems-0.903
 Carney-0.894
Token:
Token ID25
Feature activation+1.77e+00

Pos logit contributions
LLOW+4.739
tten+4.642
 Swordsman+4.330
��+4.168
FACE+4.097
Neg logit contributions
ippers-6.188
ipper-5.992
rones-5.161
lems-5.075
ploy-5.028
Token O
Token ID440
Feature activation+7.89e-01

Pos logit contributions
LLOW+1.358
tten+1.322
��+1.284
 Swordsman+1.254
FACE+1.229
Neg logit contributions
ippers-1.317
ipper-1.286
rones-1.042
lems-1.028
 Carney-1.018
Tokencar
Token ID7718
Feature activation+1.51e+00

Pos logit contributions
LLOW+0.781
tten+0.769
��+0.748
 Swordsman+0.729
ADRA+0.728
Neg logit contributions
ippers-0.410
ipper-0.395
rones-0.285
lems-0.281
lihood-0.280
Tokenina
Token ID1437
Feature activation+6.65e-01

Pos logit contributions
tten+1.007
LLOW+1.003
��+0.935
 Swordsman+0.920
FACE+0.915
Neg logit contributions
ippers-1.233
ipper-1.186
lihood-1.012
lems-1.009
ploy-1.000
Token of
Token ID286
Feature activation+1.11e+00

Pos logit contributions
LLOW+0.520
tten+0.508
��+0.497
 Swordsman+0.482
FACE+0.476
Neg logit contributions
ippers-0.484
ipper-0.473
rones-0.377
lems-0.375
 Carney-0.371
TokenK
Token ID42
Feature activation-9.44e-01

Pos logit contributions
ippers+1.376
ipper+1.353
rones+1.163
lems+1.159
 Carney+1.152
Neg logit contributions
LLOW-0.600
tten-0.575
��-0.555
 Swordsman-0.525
ADRA-0.513
Token people
Token ID661
Feature activation-4.78e-01

Pos logit contributions
ippers+0.662
ipper+0.646
rones+0.511
lems+0.509
 Carney+0.504
Neg logit contributions
LLOW-0.763
tten-0.745
��-0.729
 Swordsman-0.708
FACE-0.699
Token are
Token ID389
Feature activation+1.40e-01

Pos logit contributions
ippers+0.357
ipper+0.348
rones+0.281
lems+0.279
 Carney+0.275
Neg logit contributions
LLOW-0.365
tten-0.356
��-0.346
 Swordsman-0.337
FACE-0.333
Token still
Token ID991
Feature activation+2.05e+00

Pos logit contributions
LLOW+0.106
tten+0.103
��+0.100
 Swordsman+0.097
FACE+0.097
Neg logit contributions
ippers-0.106
ipper-0.104
rones-0.084
lems-0.083
lihood-0.082
Token coming
Token ID2406
Feature activation+1.64e+00

Pos logit contributions
LLOW+1.518
tten+1.473
��+1.405
 Swordsman+1.389
FACE+1.384
Neg logit contributions
ippers-1.553
ipper-1.523
rones-1.252
lems-1.221
lihood-1.216
Token out
Token ID503
Feature activation+7.39e+00

Pos logit contributions
LLOW+1.194
tten+1.153
��+1.115
 Swordsman+1.090
FACE+1.077
Neg logit contributions
ippers-1.267
ipper-1.237
rones-1.010
lems-0.995
 Carney-0.992
Token with
Token ID351
Feature activation+1.38e+00

Pos logit contributions
LLOW+4.934
tten+4.837
 Swordsman+4.514
 Bleach+4.487
FACE+4.485
Neg logit contributions
ippers-5.804
ipper-5.637
rones-4.670
ploy-4.613
lihood-4.587
Token shorts
Token ID22078
Feature activation+3.07e+00

Pos logit contributions
LLOW+1.056
tten+1.028
��+0.998
 Swordsman+0.977
FACE+0.961
Neg logit contributions
ippers-1.031
ipper-1.006
lems-0.806
rones-0.806
lihood-0.798
Token from
Token ID422
Feature activation-6.03e-01

Pos logit contributions
LLOW+2.294
tten+2.228
��+2.139
 Swordsman+2.107
FACE+2.085
Neg logit contributions
ippers-2.305
ipper-2.250
lems-1.822
rones-1.817
lihood-1.816
Token this
Token ID428
Feature activation+2.25e-01

Pos logit contributions
ippers+0.443
ipper+0.432
rones+0.346
lems+0.345
lihood+0.341
Neg logit contributions
LLOW-0.467
tten-0.457
��-0.445
 Swordsman-0.433
FACE-0.427
Token site
Token ID2524
Feature activation+3.41e+00

Pos logit contributions
LLOW+0.167
tten+0.163
��+0.159
 Swordsman+0.154
FACE+0.152
Neg logit contributions
ippers-0.172
ipper-0.168
rones-0.137
lems-0.136
lihood-0.134
Token the
Token ID262
Feature activation+1.86e+00

Pos logit contributions
LLOW+1.842
tten+1.798
��+1.762
 Swordsman+1.706
ADRA+1.684
Neg logit contributions
ippers-1.833
ipper-1.789
rones-1.440
lems-1.435
lihood-1.424
Token first
Token ID717
Feature activation+1.73e+00

Pos logit contributions
LLOW+1.311
tten+1.271
��+1.241
 Swordsman+1.206
FACE+1.180
Neg logit contributions
ippers-1.486
ipper-1.443
lems-1.199
rones-1.192
lihood-1.171
Token step
Token ID2239
Feature activation-1.23e+00

Pos logit contributions
LLOW+1.194
tten+1.168
��+1.130
 Swordsman+1.092
FACE+1.078
Neg logit contributions
ippers-1.425
ipper-1.384
rones-1.146
lems-1.144
ploy-1.104
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
ippers+0.819
ipper+0.798
rones+0.620
lems+0.618
 Carney+0.611
Neg logit contributions
LLOW-1.035
tten-1.011
��-0.992
 Swordsman-0.962
ADRA-0.953
Token a
Token ID257
Feature activation+1.59e+00

Pos logit contributions
ippers+0.133
ipper+0.130
rones+0.104
lems+0.103
 Carney+0.101
Neg logit contributions
LLOW-0.144
tten-0.141
��-0.137
 Swordsman-0.133
FACE-0.131
Token sweeping
Token ID18404
Feature activation+7.31e+00

Pos logit contributions
LLOW+1.167
tten+1.146
��+1.102
 Swordsman+1.076
FACE+1.066
Neg logit contributions
ippers-1.227
ipper-1.185
lems-0.968
rones-0.961
mast-0.940
Token review
Token ID2423
Feature activation+1.55e+00

Pos logit contributions
tten+5.144
LLOW+5.108
��+4.869
 Swordsman+4.745
ATH+4.725
Neg logit contributions
ippers-5.612
ipper-5.329
lems-4.394
rones-4.387
ploy-4.269
Token of
Token ID286
Feature activation+1.07e+00

Pos logit contributions
LLOW+1.192
tten+1.170
��+1.136
 Swordsman+1.104
FACE+1.091
Neg logit contributions
ippers-1.138
ipper-1.108
rones-0.892
lems-0.890
lihood-0.872
Token the
Token ID262
Feature activation+5.03e-01

Pos logit contributions
LLOW+0.818
tten+0.799
��+0.780
 Swordsman+0.753
FACE+0.746
Neg logit contributions
ippers-0.799
ipper-0.780
rones-0.627
lems-0.625
lihood-0.614
Token tobacco
Token ID11219
Feature activation-4.48e-01

Pos logit contributions
LLOW+0.392
tten+0.382
��+0.374
 Swordsman+0.363
FACE+0.358
Neg logit contributions
ippers-0.369
ipper-0.359
rones-0.287
lems-0.286
lihood-0.282
Token industry
Token ID2831
Feature activation+7.83e-01

Pos logit contributions
ippers+0.327
ipper+0.318
rones+0.254
lems+0.254
 Carney+0.250
Neg logit contributions
LLOW-0.350
tten-0.342
��-0.334
 Swordsman-0.324
FACE-0.320
Token not
Token ID407
Feature activation+9.86e-01

Pos logit contributions
LLOW+0.234
tten+0.230
��+0.223
 Swordsman+0.216
FACE+0.213
Neg logit contributions
ippers-0.219
ipper-0.214
rones-0.171
lems-0.170
ploy-0.167
Token heard
Token ID2982
Feature activation+7.84e-01

Pos logit contributions
LLOW+0.774
tten+0.761
��+0.737
 Swordsman+0.709
FACE+0.704
Neg logit contributions
ippers-0.714
ipper-0.696
rones-0.556
lems-0.553
mast-0.541
Token of
Token ID286
Feature activation+1.96e+00

Pos logit contributions
LLOW+0.607
tten+0.593
��+0.580
 Swordsman+0.560
FACE+0.554
Neg logit contributions
ippers-0.578
ipper-0.564
rones-0.451
lems-0.449
 Carney-0.443
Token the
Token ID262
Feature activation+2.18e-01

Pos logit contributions
LLOW+1.203
tten+1.155
��+1.119
 Swordsman+1.080
FACE+1.058
Neg logit contributions
ippers-1.770
ipper-1.734
rones-1.449
lems-1.442
mast-1.427
Token Republican
Token ID3415
Feature activation+2.75e+00

Pos logit contributions
LLOW+0.148
tten+0.143
��+0.139
 Swordsman+0.135
FACE+0.132
Neg logit contributions
ippers-0.182
ipper-0.178
rones-0.147
lems-0.146
lihood-0.144
Token strategist
Token ID25651
Feature activation+7.28e+00

Pos logit contributions
LLOW+2.008
tten+1.965
��+1.900
 Swordsman+1.890
ATH+1.834
Neg logit contributions
ippers-2.090
ipper-2.042
lems-1.679
rones-1.660
lihood-1.638
Token despite
Token ID3805
Feature activation-4.48e-01

Pos logit contributions
LLOW+3.906
tten+3.591
��+3.500
 Swordsman+3.447
 Bleach+3.350
Neg logit contributions
ippers-6.924
ipper-6.712
rones-5.824
lems-5.790
lihood-5.633
Token his
Token ID465
Feature activation+1.13e+00

Pos logit contributions
ippers+0.340
ipper+0.332
rones+0.268
lems+0.267
 Carney+0.263
Neg logit contributions
LLOW-0.336
tten-0.328
��-0.320
 Swordsman-0.310
FACE-0.306
Token having
Token ID1719
Feature activation+1.20e+00

Pos logit contributions
LLOW+0.858
tten+0.839
��+0.812
 Swordsman+0.790
FACE+0.784
Neg logit contributions
ippers-0.848
ipper-0.830
rones-0.671
lems-0.669
mast-0.652
Token been
Token ID587
Feature activation-1.20e+00

Pos logit contributions
LLOW+0.887
tten+0.874
��+0.844
 Swordsman+0.817
FACE+0.812
Neg logit contributions
ippers-0.921
ipper-0.902
rones-0.732
lems-0.726
mast-0.716
Token widely
Token ID6768
Feature activation+3.78e+00

Pos logit contributions
ippers+0.882
ipper+0.861
rones+0.692
lems+0.688
lihood+0.675
Neg logit contributions
LLOW-0.926
tten-0.903
��-0.881
 Swordsman-0.853
FACE-0.847
Token grapp
Token ID21338
Feature activation+2.43e+00

Pos logit contributions
LLOW+0.512
tten+0.498
��+0.485
 Swordsman+0.477
FACE+0.463
Neg logit contributions
ippers-0.563
ipper-0.548
rones-0.447
lems-0.445
lihood-0.440
Tokenler
Token ID1754
Feature activation-7.19e-01

Pos logit contributions
LLOW+2.571
tten+2.559
��+2.472
 Swordsman+2.460
FACE+2.424
Neg logit contributions
ippers-1.046
ipper-0.988
lihood-0.687
rones-0.671
 Carney-0.661
Token in
Token ID287
Feature activation-7.48e-01

Pos logit contributions
ippers+0.551
ipper+0.540
rones+0.435
lems+0.434
 Carney+0.431
Neg logit contributions
LLOW-0.534
tten-0.521
��-0.511
 Swordsman-0.490
ADRA-0.488
Token the
Token ID262
Feature activation+9.62e-01

Pos logit contributions
ippers+0.564
ipper+0.551
rones+0.443
lems+0.442
 Carney+0.437
Neg logit contributions
LLOW-0.566
tten-0.552
��-0.541
 Swordsman-0.522
ADRA-0.516
Token Street
Token ID3530
Feature activation+6.05e+00

Pos logit contributions
LLOW+0.710
tten+0.690
��+0.674
 Swordsman+0.658
FACE+0.643
Neg logit contributions
ippers-0.745
ipper-0.728
rones-0.591
lems-0.586
lihood-0.582
Token Fighter
Token ID15411
Feature activation+7.20e+00

Pos logit contributions
LLOW+3.952
tten+3.810
��+3.684
 Swordsman+3.673
FACE+3.563
Neg logit contributions
ippers-5.074
ipper-4.962
rones-4.113
lems-4.086
lihood-4.021
Token series
Token ID2168
Feature activation+2.58e+00

Pos logit contributions
LLOW+4.865
tten+4.630
��+4.546
 Swordsman+4.493
 Bleach+4.324
Neg logit contributions
ippers-5.866
ipper-5.724
lems-4.758
rones-4.717
mast-4.638
Token to
Token ID284
Feature activation+5.12e-01

Pos logit contributions
LLOW+1.821
tten+1.772
��+1.733
 Swordsman+1.681
FACE+1.650
Neg logit contributions
ippers-2.070
ipper-2.023
rones-1.661
lems-1.649
 Carney-1.629
Token ever
Token ID1683
Feature activation-1.24e+00

Pos logit contributions
LLOW+0.407
tten+0.400
��+0.387
 Swordsman+0.380
FACE+0.374
Neg logit contributions
ippers-0.364
ipper-0.355
rones-0.284
lems-0.282
lihood-0.278
Token have
Token ID423
Feature activation-1.63e-01

Pos logit contributions
ippers+0.888
ipper+0.867
rones+0.687
lems+0.685
 Carney+0.679
Neg logit contributions
LLOW-0.981
tten-0.957
��-0.941
 Swordsman-0.907
ADRA-0.901
Token a
Token ID257
Feature activation+9.56e-01

Pos logit contributions
ippers+0.118
ipper+0.115
rones+0.092
lems+0.091
 Carney+0.090
Neg logit contributions
LLOW-0.128
tten-0.125
��-0.122
 Swordsman-0.119
FACE-0.117
Token poll
Token ID3278
Feature activation+2.84e+00

Pos logit contributions
LLOW+0.946
tten+0.917
��+0.902
 Swordsman+0.848
ATH+0.828
Neg logit contributions
ippers-1.566
ipper-1.535
lems-1.324
rones-1.311
lihood-1.283
Token conducted
Token ID5952
Feature activation+4.24e-01

Pos logit contributions
LLOW+2.105
tten+2.043
��+1.995
 Swordsman+1.940
FACE+1.913
Neg logit contributions
ippers-2.177
ipper-2.116
rones-1.721
lems-1.721
mast-1.694
Token this
Token ID428
Feature activation-8.16e-01

Pos logit contributions
LLOW+0.374
tten+0.366
��+0.360
 Swordsman+0.351
FACE+0.347
Neg logit contributions
ippers-0.265
ipper-0.258
lems-0.195
rones-0.195
lihood-0.192
Token weekend
Token ID5041
Feature activation+1.77e+00

Pos logit contributions
ippers+0.746
ipper+0.732
rones+0.614
lems+0.612
 Carney+0.605
Neg logit contributions
LLOW-0.487
tten-0.471
��-0.459
 Swordsman-0.440
FACE-0.432
Token in
Token ID287
Feature activation+3.90e-01

Pos logit contributions
LLOW+1.453
tten+1.412
��+1.389
 Swordsman+1.358
FACE+1.338
Neg logit contributions
ippers-1.209
ipper-1.176
lems-0.920
rones-0.920
mast-0.902
Token Wisconsin
Token ID9279
Feature activation+7.10e+00

Pos logit contributions
LLOW+0.329
tten+0.320
��+0.313
 Swordsman+0.305
FACE+0.301
Neg logit contributions
ippers-0.262
ipper-0.255
rones-0.198
lems-0.197
mast-0.195
Token,
Token ID11
Feature activation+7.72e-01

Pos logit contributions
LLOW+5.044
tten+4.846
��+4.765
 Swordsman+4.607
FACE+4.563
Neg logit contributions
ippers-5.430
ipper-5.318
lems-4.329
rones-4.322
mast-4.278
Token another
Token ID1194
Feature activation-1.01e+00

Pos logit contributions
LLOW+0.590
tten+0.573
��+0.560
 Swordsman+0.544
FACE+0.537
Neg logit contributions
ippers-0.575
ipper-0.562
rones-0.453
lems-0.452
mast-0.444
Token state
Token ID1181
Feature activation+8.44e-01

Pos logit contributions
ippers+0.789
ipper+0.771
rones+0.625
lems+0.624
 Carney+0.613
Neg logit contributions
LLOW-0.742
tten-0.723
��-0.707
 Swordsman-0.684
FACE-0.674
Token with
Token ID351
Feature activation+3.42e-01

Pos logit contributions
LLOW+0.635
tten+0.617
��+0.605
 Swordsman+0.585
FACE+0.577
Neg logit contributions
ippers-0.639
ipper-0.625
rones-0.505
lems-0.503
mast-0.495
Token a
Token ID257
Feature activation+1.37e-01

Pos logit contributions
LLOW+0.267
tten+0.261
��+0.255
 Swordsman+0.247
FACE+0.244
Neg logit contributions
ippers-0.248
ipper-0.244
rones-0.194
lems-0.193
mast-0.191
Token,
Token ID11
Feature activation+2.36e+00

Pos logit contributions
ippers+1.563
ipper+1.529
rones+1.225
lems+1.221
 Carney+1.210
Neg logit contributions
LLOW-1.643
tten-1.611
��-1.576
 Swordsman-1.526
ADRA-1.525
Token paid
Token ID3432
Feature activation+2.01e+00

Pos logit contributions
LLOW+1.788
tten+1.721
��+1.672
 Swordsman+1.644
FACE+1.622
Neg logit contributions
ippers-1.774
ipper-1.738
rones-1.402
lihood-1.399
lems-1.385
Token for
Token ID329
Feature activation+2.00e+00

Pos logit contributions
LLOW+1.710
tten+1.663
��+1.607
 Swordsman+1.580
FACE+1.574
Neg logit contributions
ippers-1.305
ipper-1.271
lihood-0.998
lems-0.983
rones-0.983
Token by
Token ID416
Feature activation-1.77e-01

Pos logit contributions
LLOW+1.767
tten+1.709
��+1.670
 Swordsman+1.665
FACE+1.631
Neg logit contributions
ippers-1.235
ipper-1.190
lems-0.910
ploy-0.907
rones-0.894
Token George
Token ID4502
Feature activation-1.77e-01

Pos logit contributions
ippers+0.137
ipper+0.134
lems+0.108
rones+0.108
lihood+0.106
Neg logit contributions
LLOW-0.131
tten-0.128
��-0.124
 Swordsman-0.121
FACE-0.119
Token Soros
Token ID27900
Feature activation+7.07e+00

Pos logit contributions
ippers+0.149
ipper+0.147
rones+0.121
lems+0.121
lihood+0.119
Neg logit contributions
LLOW-0.119
tten-0.115
��-0.112
 Swordsman-0.109
FACE-0.107
Token's
Token ID338
Feature activation+5.53e-01

Pos logit contributions
LLOW+4.756
tten+4.487
 Swordsman+4.325
��+4.270
FACE+4.229
Neg logit contributions
ippers-5.647
ipper-5.506
lems-4.557
rones-4.510
lihood-4.500
Token pre
Token ID662
Feature activation+2.80e+00

Pos logit contributions
LLOW+0.448
tten+0.435
��+0.424
 Swordsman+0.415
FACE+0.408
Neg logit contributions
ippers-0.388
ipper-0.379
rones-0.299
lems-0.298
mast-0.293
Token-
Token ID12
Feature activation+1.39e+00

Pos logit contributions
LLOW+2.187
tten+2.173
��+2.088
FACE+2.038
 Swordsman+2.023
Neg logit contributions
ippers-1.985
ipper-1.921
lems-1.539
lihood-1.519
rones-1.513
Tokentax
Token ID19290
Feature activation-8.35e-01

Pos logit contributions
LLOW+1.021
tten+1.004
��+0.970
FACE+0.940
 Swordsman+0.932
Neg logit contributions
ippers-1.079
ipper-1.051
lems-0.851
lihood-0.846
rones-0.844
Token dollars
Token ID5054
Feature activation-1.66e+00

Pos logit contributions
ippers+0.597
ipper+0.583
rones+0.463
lems+0.461
 Carney+0.457
Neg logit contributions
LLOW-0.664
tten-0.648
��-0.635
 Swordsman-0.615
ADRA-0.609
Token.
Token ID13
Feature activation+1.92e+00

Pos logit contributions
LLOW+1.390
tten+1.369
��+1.328
 Swordsman+1.279
ADRA+1.260
Neg logit contributions
ippers-1.421
ipper-1.388
 Carney-1.119
rones-1.115
lems-1.110
Token Fro
Token ID9734
Feature activation+1.87e+00

Pos logit contributions
LLOW+1.420
tten+1.358
 Swordsman+1.323
��+1.310
FACE+1.287
Neg logit contributions
ippers-1.491
ipper-1.455
rones-1.190
ploy-1.168
lems-1.165
Tokendo
Token ID4598
Feature activation+2.85e+00

Pos logit contributions
LLOW+1.561
tten+1.543
��+1.459
 Swordsman+1.429
FACE+1.428
Neg logit contributions
ippers-1.252
ipper-1.206
rones-0.960
 Carney-0.958
lihood-0.945
Token falls
Token ID8953
Feature activation+3.50e+00

Pos logit contributions
LLOW+2.183
tten+2.147
��+2.076
 Swordsman+2.058
FACE+2.005
Neg logit contributions
ippers-2.075
ipper-2.026
rones-1.612
lems-1.598
ploy-1.585
Token to
Token ID284
Feature activation+4.31e+00

Pos logit contributions
LLOW+2.523
tten+2.474
��+2.354
 Swordsman+2.350
FACE+2.301
Neg logit contributions
ippers-2.700
ipper-2.623
rones-2.156
 Carney-2.129
ploy-2.102
Token Shel
Token ID15325
Feature activation+7.06e+00

Pos logit contributions
LLOW+3.068
tten+3.050
��+2.884
 Swordsman+2.871
ADRA+2.798
Neg logit contributions
ippers-3.373
ipper-3.303
rones-2.717
 Carney-2.700
ploy-2.664
Tokenob
Token ID672
Feature activation+1.17e+00

Pos logit contributions
tten+6.559
LLOW+6.534
 Swordsman+6.178
icide+5.979
ATH+5.965
Neg logit contributions
ippers-3.481
ipper-3.405
 Carney-2.711
lihood-2.655
rones-2.517
Token's
Token ID338
Feature activation+4.98e-01

Pos logit contributions
LLOW+0.920
tten+0.899
��+0.880
 Swordsman+0.852
ADRA+0.841
Neg logit contributions
ippers-0.851
ipper-0.831
rones-0.661
lems-0.658
 Carney-0.652
Token sting
Token ID24276
Feature activation+7.86e-01

Pos logit contributions
LLOW+0.372
tten+0.363
��+0.355
 Swordsman+0.345
ADRA+0.339
Neg logit contributions
ippers-0.379
ipper-0.370
rones-0.300
 Carney-0.297
lems-0.297
Token.
Token ID13
Feature activation+2.67e-01

Pos logit contributions
LLOW+0.626
tten+0.611
��+0.598
 Swordsman+0.580
ADRA+0.572
Neg logit contributions
ippers-0.561
ipper-0.547
rones-0.434
lems-0.432
 Carney-0.429
Token But
Token ID887
Feature activation+1.37e+00

Pos logit contributions
LLOW+0.202
tten+0.196
��+0.190
 Swordsman+0.188
FACE+0.184
Neg logit contributions
ippers-0.202
ipper-0.197
rones-0.159
lems-0.157
ploy-0.156
TokenBefore
Token ID8421
Feature activation+3.87e+00

Pos logit contributions
ippers+0.350
ipper+0.343
rones+0.285
lems+0.284
 Carney+0.282
Neg logit contributions
LLOW-0.260
tten-0.252
��-0.245
 Swordsman-0.236
ADRA-0.233
Token the
Token ID262
Feature activation+6.18e-01

Pos logit contributions
LLOW+2.722
tten+2.680
��+2.551
 Swordsman+2.530
FACE+2.483
Neg logit contributions
ippers-3.043
ipper-2.965
rones-2.472
lems-2.454
mast-2.403
Token gameplay
Token ID11327
Feature activation+3.20e+00

Pos logit contributions
LLOW+0.447
tten+0.436
��+0.424
 Swordsman+0.414
FACE+0.405
Neg logit contributions
ippers-0.484
ipper-0.474
rones-0.387
lems-0.385
mast-0.379
Token proved
Token ID8302
Feature activation-1.19e+00

Pos logit contributions
LLOW+2.474
tten+2.451
��+2.313
 Swordsman+2.303
FACE+2.264
Neg logit contributions
ippers-2.327
ipper-2.272
rones-1.836
lems-1.820
ploy-1.799
Token Donkey
Token ID43823
Feature activation+2.90e+00

Pos logit contributions
ippers+0.904
ipper+0.884
rones+0.711
lems+0.710
 Carney+0.704
Neg logit contributions
LLOW-0.896
tten-0.873
��-0.855
 Swordsman-0.825
ADRA-0.816
Token Kong
Token ID9071
Feature activation+7.03e+00

Pos logit contributions
LLOW+0.815
tten+0.747
��+0.686
 Swordsman+0.656
FACE+0.628
Neg logit contributions
ippers-3.543
ipper-3.491
lems-3.084
rones-3.081
lihood-3.073
Token Country
Token ID12946
Feature activation+3.51e+00

Pos logit contributions
LLOW+4.089
tten+3.976
 Swordsman+3.808
��+3.715
ADRA+3.658
Neg logit contributions
ippers-6.189
ipper-6.068
rones-5.194
lems-5.146
mast-5.107
Token 2
Token ID362
Feature activation+1.65e+00

Pos logit contributions
LLOW+2.549
tten+2.488
��+2.409
 Swordsman+2.350
ADRA+2.300
Neg logit contributions
ippers-2.720
ipper-2.664
rones-2.163
lems-2.146
mast-2.135
Token:
Token ID25
Feature activation+2.36e+00

Pos logit contributions
LLOW+1.273
tten+1.247
��+1.212
 Swordsman+1.178
FACE+1.160
Neg logit contributions
ippers-1.211
ipper-1.184
rones-0.947
lems-0.944
 Carney-0.933
Token D
Token ID360
Feature activation+1.18e+00

Pos logit contributions
LLOW+1.555
tten+1.505
��+1.468
 Swordsman+1.419
ADRA+1.394
Neg logit contributions
ippers-2.006
ipper-1.967
rones-1.627
lems-1.620
 Carney-1.609
Tokeniddy
Token ID34208
Feature activation+3.97e+00

Pos logit contributions
LLOW+0.876
tten+0.854
��+0.834
 Swordsman+0.805
FACE+0.796
Neg logit contributions
ippers-0.905
ipper-0.884
rones-0.714
lems-0.712
 Carney-0.707
Token release
Token ID2650
Feature activation+1.51e+00

Pos logit contributions
LLOW+0.080
tten+0.078
��+0.077
 Swordsman+0.074
FACE+0.073
Neg logit contributions
ippers-0.073
ipper-0.072
rones-0.057
lems-0.057
 Carney-0.056
Token date
Token ID3128
Feature activation+2.19e+00

Pos logit contributions
LLOW+1.307
tten+1.282
��+1.241
 Swordsman+1.226
FACE+1.195
Neg logit contributions
ippers-0.963
ipper-0.938
rones-0.733
lems-0.729
 Carney-0.711
Token for
Token ID329
Feature activation+2.96e+00

Pos logit contributions
LLOW+1.746
tten+1.703
��+1.640
 Swordsman+1.629
FACE+1.586
Neg logit contributions
ippers-1.544
ipper-1.511
rones-1.209
lems-1.200
 Carney-1.171
Token "
Token ID366
Feature activation+1.79e+00

Pos logit contributions
LLOW+2.095
tten+1.999
��+1.950
 Swordsman+1.926
FACE+1.865
Neg logit contributions
ippers-2.370
ipper-2.310
rones-1.921
lems-1.899
ploy-1.874
TokenFinal
Token ID19006
Feature activation+2.27e+00

Pos logit contributions
LLOW+0.989
tten+0.948
��+0.923
 Swordsman+0.881
FACE+0.874
Neg logit contributions
ippers-1.711
ipper-1.679
rones-1.425
lems-1.417
 Carney-1.413
Token Fantasy
Token ID10982
Feature activation+7.01e+00

Pos logit contributions
LLOW+1.822
tten+1.778
��+1.743
 Swordsman+1.733
FACE+1.674
Neg logit contributions
ippers-1.598
ipper-1.557
rones-1.246
lems-1.224
 Carney-1.202
Token V
Token ID569
Feature activation+4.11e+00

Pos logit contributions
LLOW+4.877
tten+4.780
 Swordsman+4.623
��+4.546
 Bleach+4.399
Neg logit contributions
ippers-5.521
ipper-5.369
rones-4.487
lems-4.453
ploy-4.267
TokenX
Token ID55
Feature activation+1.16e+00

Pos logit contributions
LLOW+2.636
tten+2.554
��+2.458
 Swordsman+2.394
FACE+2.350
Neg logit contributions
ippers-3.521
ipper-3.456
lems-2.906
rones-2.906
 Carney-2.875
Token"
Token ID1
Feature activation+6.30e-01

Pos logit contributions
LLOW+0.740
tten+0.717
��+0.700
 Swordsman+0.673
FACE+0.662
Neg logit contributions
ippers-1.019
ipper-0.998
rones-0.832
lems-0.831
 Carney-0.821
Token will
Token ID481
Feature activation+1.70e-01

Pos logit contributions
LLOW+0.509
tten+0.497
��+0.485
 Swordsman+0.473
FACE+0.465
Neg logit contributions
ippers-0.441
ipper-0.430
rones-0.340
lems-0.339
 Carney-0.335
Token be
Token ID307
Feature activation+1.11e+00

Pos logit contributions
LLOW+0.131
tten+0.128
��+0.124
 Swordsman+0.121
FACE+0.119
Neg logit contributions
ippers-0.125
ipper-0.122
rones-0.098
lems-0.098
 Carney-0.097
Token9
Token ID24
Feature activation+6.77e-01

Pos logit contributions
ippers+1.557
ipper+1.523
rones+1.219
lems+1.214
 Carney+1.204
Neg logit contributions
LLOW-1.622
tten-1.584
��-1.555
 Swordsman-1.498
ADRA-1.483
Token million
Token ID1510
Feature activation+2.39e+00

Pos logit contributions
LLOW+0.430
tten+0.417
��+0.406
 Swordsman+0.390
ADRA+0.384
Neg logit contributions
ippers-0.594
ipper-0.582
rones-0.484
lems-0.483
 Carney-0.479
Token in
Token ID287
Feature activation+1.54e+00

Pos logit contributions
LLOW+1.821
tten+1.761
��+1.723
 Swordsman+1.695
FACE+1.675
Neg logit contributions
ippers-1.789
ipper-1.744
rones-1.390
lems-1.387
lihood-1.377
Token April
Token ID3035
Feature activation-2.92e+00

Pos logit contributions
LLOW+1.147
tten+1.112
��+1.089
 Swordsman+1.060
FACE+1.053
Neg logit contributions
ippers-1.176
ipper-1.150
lems-0.924
rones-0.922
lihood-0.919
Token,
Token ID11
Feature activation-2.33e-01

Pos logit contributions
ippers+1.954
ipper+1.903
rones+1.510
 Carney+1.499
lems+1.493
Neg logit contributions
LLOW-2.418
tten-2.389
��-2.315
ADRA-2.265
 Swordsman-2.246
Token narrowly
Token ID26167
Feature activation+6.97e+00

Pos logit contributions
ippers+0.184
ipper+0.180
rones+0.147
lems+0.146
 Carney+0.145
Neg logit contributions
LLOW-0.168
tten-0.164
��-0.160
 Swordsman-0.154
ADRA-0.152
Token in
Token ID287
Feature activation+1.80e+00

Pos logit contributions
tten+3.977
LLOW+3.976
��+3.704
 Swordsman+3.691
 Bleach+3.631
Neg logit contributions
ippers-6.137
ipper-6.082
rones-5.183
lems-5.109
ploy-5.008
Tokenching
Token ID10813
Feature activation+1.20e+00

Pos logit contributions
LLOW+1.424
tten+1.392
��+1.354
 Swordsman+1.303
FACE+1.294
Neg logit contributions
ippers-1.292
ipper-1.263
rones-1.004
lems-0.998
lihood-0.991
Token out
Token ID503
Feature activation+1.26e+00

Pos logit contributions
LLOW+0.862
tten+0.840
��+0.810
 Swordsman+0.800
FACE+0.793
Neg logit contributions
ippers-0.944
ipper-0.925
rones-0.751
lems-0.745
ploy-0.740
Token Mrs
Token ID9074
Feature activation-4.16e+00

Pos logit contributions
LLOW+0.923
tten+0.904
��+0.877
 Swordsman+0.859
FACE+0.844
Neg logit contributions
ippers-0.973
ipper-0.952
rones-0.773
lems-0.767
ploy-0.755
Token.
Token ID13
Feature activation-1.70e+00

Pos logit contributions
ippers+2.897
ipper+2.826
 Carney+2.244
lems+2.230
rones+2.220
Neg logit contributions
LLOW-3.352
tten-3.290
��-3.286
ADRA-3.185
 Swordsman-3.095
Token risk
Token ID2526
Feature activation+6.08e-01

Pos logit contributions
LLOW+0.612
tten+0.597
��+0.584
FACE+0.564
 Swordsman+0.561
Neg logit contributions
ippers-0.513
ipper-0.498
lems-0.394
rones-0.394
 Carney-0.385
Token of
Token ID286
Feature activation+6.49e-01

Pos logit contributions
LLOW+0.480
tten+0.468
��+0.458
 Swordsman+0.443
FACE+0.439
Neg logit contributions
ippers-0.438
ipper-0.428
rones-0.341
lems-0.340
 Carney-0.335
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
LLOW+0.436
tten+0.425
��+0.414
 Swordsman+0.398
ADRA+0.392
Neg logit contributions
ippers-0.543
ipper-0.532
rones-0.439
lems-0.439
 Carney-0.432
Token situation
Token ID3074
Feature activation+2.79e+00

Pos logit contributions
LLOW+0.690
tten+0.669
��+0.652
 Swordsman+0.626
ADRA+0.617
Neg logit contributions
ippers-0.923
ipper-0.904
rones-0.753
lems-0.749
 Carney-0.740
Token in
Token ID287
Feature activation+1.90e+00

Pos logit contributions
LLOW+2.054
tten+2.004
��+1.958
 Swordsman+1.882
FACE+1.870
Neg logit contributions
ippers-2.141
ipper-2.082
rones-1.704
lems-1.700
lihood-1.667
Token Chennai
Token ID47678
Feature activation+6.88e+00

Pos logit contributions
LLOW+1.312
tten+1.272
��+1.231
 Swordsman+1.188
ADRA+1.171
Neg logit contributions
ippers-1.557
ipper-1.525
rones-1.264
lems-1.259
lihood-1.239
Token becoming
Token ID5033
Feature activation+1.89e+00

Pos logit contributions
LLOW+4.914
tten+4.738
��+4.646
 Swordsman+4.474
FACE+4.433
Neg logit contributions
ippers-5.177
ipper-5.041
lihood-4.185
rones-4.175
lems-4.170
Token even
Token ID772
Feature activation-8.30e-01

Pos logit contributions
LLOW+1.363
tten+1.344
��+1.314
 Swordsman+1.250
FACE+1.248
Neg logit contributions
ippers-1.483
ipper-1.437
rones-1.188
lems-1.171
lihood-1.158
Token worse
Token ID4785
Feature activation+6.17e-01

Pos logit contributions
ippers+0.677
ipper+0.661
rones+0.543
lems+0.541
 Carney+0.535
Neg logit contributions
LLOW-0.577
tten-0.563
��-0.549
 Swordsman-0.528
FACE-0.523
Token over
Token ID625
Feature activation+1.41e+00

Pos logit contributions
LLOW+0.452
tten+0.439
��+0.428
 Swordsman+0.414
FACE+0.410
Neg logit contributions
ippers-0.480
ipper-0.469
rones-0.380
lems-0.379
 Carney-0.374
Token the
Token ID262
Feature activation+3.89e-01

Pos logit contributions
LLOW+1.097
tten+1.069
��+1.049
 Swordsman+1.015
ADRA+1.004
Neg logit contributions
ippers-1.038
ipper-1.014
rones-0.809
lems-0.807
 Carney-0.801
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
LLOW+0.526
tten+0.510
��+0.499
 Swordsman+0.484
FACE+0.479
Neg logit contributions
ippers-0.539
ipper-0.526
lems-0.425
rones-0.424
 Carney-0.419
Token Recap
Token ID46585
Feature activation+1.30e+00

Pos logit contributions
LLOW+0.864
tten+0.838
��+0.806
FACE+0.795
 Swordsman+0.792
Neg logit contributions
ippers-0.785
ipper-0.767
lems-0.616
rones-0.608
lihood-0.605
Token San
Token ID2986
Feature activation-1.07e+00

Pos logit contributions
LLOW+1.024
tten+0.989
��+0.969
 Swordsman+0.941
FACE+0.934
Neg logit contributions
ippers-0.938
ipper-0.913
lems-0.731
rones-0.727
lihood-0.718
Token Juan
Token ID16852
Feature activation+3.90e-01

Pos logit contributions
ippers+0.877
ipper+0.858
lems+0.703
rones+0.700
 Carney+0.695
Neg logit contributions
LLOW-0.738
tten-0.718
��-0.702
 Swordsman-0.675
FACE-0.666
Token Del
Token ID4216
Feature activation+1.14e+00

Pos logit contributions
LLOW+0.332
tten+0.323
��+0.317
 Swordsman+0.310
ADRA+0.306
Neg logit contributions
ippers-0.257
ipper-0.250
lems-0.195
rones-0.193
lihood-0.190
Token Sur
Token ID4198
Feature activation+6.87e+00

Pos logit contributions
LLOW+0.855
tten+0.832
��+0.801
 Swordsman+0.793
FACE+0.781
Neg logit contributions
ippers-0.866
ipper-0.844
lems-0.684
rones-0.677
lihood-0.670
Token Episode
Token ID7922
Feature activation-1.54e+00

Pos logit contributions
LLOW+5.072
tten+4.777
��+4.684
FACE+4.636
 Swordsman+4.570
Neg logit contributions
ippers-5.127
ipper-4.938
lems-4.018
ploy-3.993
lihood-3.950
Token 5
Token ID642
Feature activation+9.03e-01

Pos logit contributions
ippers+1.168
ipper+1.142
rones+0.920
lems+0.915
 Carney+0.910
Neg logit contributions
LLOW-1.151
tten-1.123
��-1.100
 Swordsman-1.062
ADRA-1.052
Token
Token ID198
Feature activation-2.68e-01

Pos logit contributions
LLOW+0.694
tten+0.670
��+0.655
 Swordsman+0.638
FACE+0.631
Neg logit contributions
ippers-0.672
ipper-0.655
lems-0.528
rones-0.525
lihood-0.522
Token
Token ID198
Feature activation-8.32e-02

Pos logit contributions
ippers+0.185
ipper+0.180
rones+0.142
lems+0.141
 Carney+0.139
Neg logit contributions
LLOW-0.220
tten-0.214
��-0.209
 Swordsman-0.203
FACE-0.202
TokenCoach
Token ID40677
Feature activation+2.13e+00

Pos logit contributions
ippers+0.070
ipper+0.069
lems+0.057
rones+0.057
 Carney+0.057
Neg logit contributions
LLOW-0.056
tten-0.053
��-0.052
FACE-0.051
 Swordsman-0.050
Token details
Token ID3307
Feature activation+2.72e+00

Pos logit contributions
LLOW+0.413
tten+0.400
��+0.387
 Swordsman+0.377
FACE+0.371
Neg logit contributions
ippers-0.475
ipper-0.464
rones-0.380
lems-0.378
ploy-0.374
Token and
Token ID290
Feature activation+4.83e-01

Pos logit contributions
LLOW+1.914
tten+1.849
��+1.804
 Swordsman+1.744
FACE+1.719
Neg logit contributions
ippers-2.185
ipper-2.136
rones-1.749
lems-1.746
lihood-1.732
Token analysis
Token ID3781
Feature activation+2.83e+00

Pos logit contributions
LLOW+0.373
tten+0.362
��+0.353
 Swordsman+0.344
FACE+0.340
Neg logit contributions
ippers-0.356
ipper-0.349
rones-0.279
lems-0.278
ploy-0.273
Token.
Token ID13
Feature activation+1.56e+00

Pos logit contributions
LLOW+2.004
tten+1.938
��+1.886
 Swordsman+1.820
FACE+1.799
Neg logit contributions
ippers-2.266
ipper-2.218
rones-1.810
lems-1.807
lihood-1.792
Token<|endoftext|>
Token ID50256
Feature activation+4.01e+00

Pos logit contributions
LLOW+1.152
tten+1.104
��+1.080
 Swordsman+1.053
FACE+1.039
Neg logit contributions
ippers-1.218
ipper-1.193
rones-0.967
lems-0.962
lihood-0.954
TokenSym
Token ID43094
Feature activation+6.87e+00

Pos logit contributions
LLOW+2.676
tten+2.548
FACE+2.454
��+2.440
ATH+2.413
Neg logit contributions
ippers-3.338
ipper-3.272
 Carney-2.730
rones-2.706
lihood-2.702
Tokenone
Token ID505
Feature activation-2.73e+00

Pos logit contributions
tten+4.829
LLOW+4.826
��+4.554
 Swordsman+4.510
FACE+4.496
Neg logit contributions
ippers-5.300
ipper-5.155
lems-4.165
 Carney-4.164
rones-4.141
Token Sanders
Token ID5831
Feature activation+2.39e-01

Pos logit contributions
ippers+2.077
ipper+2.031
rones+1.637
lems+1.631
 Carney+1.618
Neg logit contributions
LLOW-2.047
tten-1.994
��-1.953
 Swordsman-1.886
ADRA-1.865
Token was
Token ID373
Feature activation-5.12e-03

Pos logit contributions
LLOW+0.187
tten+0.183
��+0.179
 Swordsman+0.174
FACE+0.172
Neg logit contributions
ippers-0.173
ipper-0.169
rones-0.135
lems-0.134
lihood-0.132
Token not
Token ID407
Feature activation+4.33e-01

Pos logit contributions
ippers+0.004
ipper+0.004
rones+0.003
lems+0.003
lihood+0.003
Neg logit contributions
LLOW-0.004
tten-0.004
��-0.004
 Swordsman-0.004
FACE-0.004
Token having
Token ID1719
Feature activation-1.47e-01

Pos logit contributions
LLOW+0.336
tten+0.329
��+0.320
 Swordsman+0.311
FACE+0.308
Neg logit contributions
ippers-0.318
ipper-0.310
rones-0.249
lems-0.247
lihood-0.242
Token at
Token ID379
Feature activation+1.27e+00

Pos logit contributions
LLOW+0.974
tten+0.951
��+0.919
 Swordsman+0.901
FACE+0.888
Neg logit contributions
ippers-0.907
ipper-0.890
rones-0.711
lems-0.705
mast-0.693
Token town
Token ID3240
Feature activation+1.05e+00

Pos logit contributions
LLOW+0.963
tten+0.939
��+0.916
 Swordsman+0.892
FACE+0.877
Neg logit contributions
ippers-0.954
ipper-0.934
rones-0.749
lems-0.747
lihood-0.736
Token meetings
Token ID8292
Feature activation+1.14e+00

Pos logit contributions
LLOW+0.964
tten+0.940
��+0.928
 Swordsman+0.893
FACE+0.890
Neg logit contributions
ippers-0.615
ipper-0.603
lems-0.449
rones-0.448
lihood-0.442
Token in
Token ID287
Feature activation+6.67e-01

Pos logit contributions
LLOW+0.892
tten+0.873
��+0.843
 Swordsman+0.825
FACE+0.810
Neg logit contributions
ippers-0.830
ipper-0.814
lems-0.645
rones-0.642
mast-0.631
Token New
Token ID968
Feature activation-1.05e+00

Pos logit contributions
LLOW+0.530
tten+0.517
��+0.503
 Swordsman+0.490
FACE+0.482
Neg logit contributions
ippers-0.480
ipper-0.469
lems-0.372
rones-0.372
mast-0.366
Token Hampshire
Token ID13910
Feature activation+6.85e+00

Pos logit contributions
ippers+0.670
ipper+0.652
rones+0.503
lems+0.502
 Carney+0.501
Neg logit contributions
LLOW-0.911
tten-0.886
��-0.873
 Swordsman-0.846
ADRA-0.843
Token and
Token ID290
Feature activation+1.13e+00

Pos logit contributions
LLOW+4.972
tten+4.868
 Swordsman+4.618
��+4.567
FACE+4.510
Neg logit contributions
ippers-5.010
ipper-4.949
lems-3.976
rones-3.928
lihood-3.897
Token Iowa
Token ID9406
Feature activation+4.35e+00

Pos logit contributions
LLOW+0.884
tten+0.864
��+0.840
 Swordsman+0.820
FACE+0.807
Neg logit contributions
ippers-0.815
ipper-0.798
rones-0.634
lems-0.633
mast-0.620
Token are
Token ID389
Feature activation+7.53e-01

Pos logit contributions
LLOW+3.331
tten+3.272
��+3.154
 Swordsman+3.069
FACE+3.043
Neg logit contributions
ippers-3.119
ipper-3.081
lems-2.433
rones-2.405
lihood-2.392
Token sending
Token ID7216
Feature activation+9.84e-01

Pos logit contributions
LLOW+0.596
tten+0.585
��+0.571
 Swordsman+0.553
FACE+0.548
Neg logit contributions
ippers-0.542
ipper-0.530
rones-0.421
lems-0.419
mast-0.411
Token a
Token ID257
Feature activation+7.31e-02

Pos logit contributions
LLOW+0.770
tten+0.751
��+0.736
 Swordsman+0.708
FACE+0.701
Neg logit contributions
ippers-0.715
ipper-0.702
rones-0.558
lems-0.555
lihood-0.549
Tokencom
Token ID785
Feature activation+1.56e+00

Pos logit contributions
ippers+1.884
ipper+1.842
rones+1.482
lems+1.472
 Carney+1.462
Neg logit contributions
LLOW-1.860
tten-1.813
��-1.784
 Swordsman-1.718
ADRA-1.706
Token
Token ID198
Feature activation+9.21e-01

Pos logit contributions
LLOW+1.146
tten+1.111
��+1.082
 Swordsman+1.049
FACE+1.040
Neg logit contributions
ippers-1.213
ipper-1.186
lems-0.961
rones-0.961
lihood-0.951
Token
Token ID198
Feature activation+7.68e-01

Pos logit contributions
LLOW+0.735
tten+0.712
��+0.687
 Swordsman+0.678
FACE+0.674
Neg logit contributions
ippers-0.658
ipper-0.640
rones-0.507
lems-0.505
lihood-0.501
TokenBy
Token ID3886
Feature activation+1.99e+00

Pos logit contributions
LLOW+0.517
tten+0.502
��+0.486
FACE+0.468
 Swordsman+0.467
Neg logit contributions
ippers-0.643
ipper-0.630
rones-0.519
lems-0.517
 Carney-0.516
Token the
Token ID262
Feature activation+1.90e+00

Pos logit contributions
LLOW+1.489
tten+1.455
��+1.408
 Swordsman+1.359
FACE+1.341
Neg logit contributions
ippers-1.524
ipper-1.485
lems-1.206
rones-1.197
lihood-1.176
Token numbers
Token ID3146
Feature activation+6.84e+00

Pos logit contributions
LLOW+1.394
tten+1.332
��+1.312
 Swordsman+1.273
FACE+1.238
Neg logit contributions
ippers-1.506
ipper-1.472
lems-1.188
rones-1.183
lihood-1.173
Token
Token ID198
Feature activation+6.96e-01

Pos logit contributions
LLOW+4.954
tten+4.754
��+4.579
 Swordsman+4.498
FACE+4.430
Neg logit contributions
ippers-5.182
ipper-5.064
lems-4.151
rones-4.105
lihood-4.063
Token
Token ID198
Feature activation+5.69e-01

Pos logit contributions
LLOW+0.554
tten+0.537
��+0.519
 Swordsman+0.511
FACE+0.509
Neg logit contributions
ippers-0.498
ipper-0.485
rones-0.384
lems-0.382
lihood-0.378
Token12
Token ID1065
Feature activation+9.52e-01

Pos logit contributions
LLOW+0.380
tten+0.369
��+0.357
FACE+0.345
 Swordsman+0.343
Neg logit contributions
ippers-0.480
ipper-0.472
rones-0.388
lems-0.387
 Carney-0.386
Token,
Token ID11
Feature activation-2.84e-01

Pos logit contributions
LLOW+0.719
tten+0.702
��+0.686
 Swordsman+0.667
FACE+0.653
Neg logit contributions
ippers-0.719
ipper-0.705
rones-0.565
lems-0.563
 Carney-0.558
Token000
Token ID830
Feature activation+2.68e+00

Pos logit contributions
ippers+0.242
ipper+0.237
rones+0.196
lems+0.196
 Carney+0.194
Neg logit contributions
LLOW-0.187
tten-0.182
��-0.177
 Swordsman-0.171
ADRA-0.168
Token we
Token ID356
Feature activation-5.92e-03

Pos logit contributions
LLOW+0.123
tten+0.121
��+0.118
 Swordsman+0.115
FACE+0.114
Neg logit contributions
ippers-0.099
ipper-0.096
rones-0.075
lems-0.075
lihood-0.074
Token
Token ID447
Feature activation-1.06e+00

Pos logit contributions
ippers+0.004
ipper+0.004
rones+0.003
lems+0.003
 Carney+0.003
Neg logit contributions
LLOW-0.005
tten-0.004
��-0.004
 Swordsman-0.004
FACE-0.004
Token
Token ID247
Feature activation-1.28e+00

Pos logit contributions
ippers+0.768
ipper+0.750
rones+0.600
lems+0.598
lihood+0.594
Neg logit contributions
LLOW-0.830
tten-0.806
��-0.805
 Swordsman-0.759
ADRA-0.756
Tokenll
Token ID297
Feature activation+1.29e-01

Pos logit contributions
ippers+0.916
ipper+0.893
rones+0.710
lems+0.706
 Carney+0.701
Neg logit contributions
LLOW-1.016
tten-0.996
��-0.972
 Swordsman-0.940
FACE-0.929
Token come
Token ID1282
Feature activation+1.36e-01

Pos logit contributions
LLOW+0.105
tten+0.103
��+0.100
 Swordsman+0.098
FACE+0.096
Neg logit contributions
ippers-0.089
ipper-0.087
rones-0.069
lems-0.068
 Carney-0.068
Token out
Token ID503
Feature activation+6.83e+00

Pos logit contributions
LLOW+0.093
tten+0.090
��+0.087
 Swordsman+0.085
FACE+0.083
Neg logit contributions
ippers-0.113
ipper-0.110
rones-0.091
lems-0.091
 Carney-0.090
Token on
Token ID319
Feature activation+6.37e-01

Pos logit contributions
LLOW+4.731
tten+4.634
 Swordsman+4.513
��+4.314
 Bleach+4.312
Neg logit contributions
ippers-5.199
ipper-5.017
rones-4.127
lems-4.093
lihood-4.076
Token top
Token ID1353
Feature activation-9.84e-01

Pos logit contributions
LLOW+0.353
tten+0.346
��+0.333
 Swordsman+0.319
FACE+0.313
Neg logit contributions
ippers-0.607
ipper-0.594
lems-0.507
rones-0.503
lihood-0.498
Token.
Token ID13
Feature activation-8.18e-01

Pos logit contributions
ippers+0.726
ipper+0.709
rones+0.567
lems+0.565
 Carney+0.559
Neg logit contributions
LLOW-0.760
tten-0.741
��-0.726
 Swordsman-0.702
FACE-0.693
Token
Token ID447
Feature activation-1.64e+00

Pos logit contributions
ippers+0.563
ipper+0.548
rones+0.429
lems+0.428
 Carney+0.421
Neg logit contributions
LLOW-0.676
tten-0.658
��-0.646
 Swordsman-0.628
FACE-0.621
Token
Token ID251
Feature activation-6.94e-01

Pos logit contributions
ippers+1.268
ipper+1.240
rones+1.003
lems+1.000
 Carney+0.991
Neg logit contributions
LLOW-1.207
tten-1.175
��-1.150
 Swordsman-1.110
ADRA-1.097
Token her
Token ID607
Feature activation-3.71e-01

Pos logit contributions
LLOW+2.237
tten+2.145
��+2.102
 Swordsman+2.053
ADRA+2.018
Neg logit contributions
ippers-2.293
ipper-2.219
rones-1.823
lems-1.810
mast-1.773
Token personal
Token ID2614
Feature activation+9.83e-01

Pos logit contributions
ippers+0.276
ipper+0.269
rones+0.216
lems+0.215
 Carney+0.212
Neg logit contributions
LLOW-0.285
tten-0.278
��-0.272
 Swordsman-0.264
FACE-0.260
Token story
Token ID1621
Feature activation-3.31e-01

Pos logit contributions
LLOW+0.671
tten+0.654
��+0.633
 Swordsman+0.618
FACE+0.607
Neg logit contributions
ippers-0.812
ipper-0.791
rones-0.653
lems-0.650
mast-0.645
Token as
Token ID355
Feature activation-8.50e-01

Pos logit contributions
ippers+0.254
ipper+0.248
rones+0.201
lems+0.200
 Carney+0.198
Neg logit contributions
LLOW-0.246
tten-0.239
��-0.234
 Swordsman-0.226
ADRA-0.224
Token supporting
Token ID6493
Feature activation-3.49e+00

Pos logit contributions
ippers+0.600
ipper+0.584
rones+0.466
lems+0.463
lihood+0.454
Neg logit contributions
LLOW-0.685
tten-0.667
��-0.654
 Swordsman-0.634
ADRA-0.629
Token evidence
Token ID2370
Feature activation-8.35e+00

Pos logit contributions
ippers+2.194
ipper+2.133
rones+1.625
lems+1.618
 Carney+1.606
Neg logit contributions
LLOW-3.075
tten-3.009
��-2.960
 Swordsman-2.872
ADRA-2.847
Token.
Token ID13
Feature activation-6.66e-01

Pos logit contributions
ippers+5.384
ipper+5.259
 Carney+4.138
lems+4.110
lihood+4.031
Neg logit contributions
LLOW-6.939
tten-6.722
��-6.652
ADRA-6.475
 Swordsman-6.307
Token
Token ID198
Feature activation+1.76e-01

Pos logit contributions
ippers+0.487
ipper+0.473
rones+0.381
lems+0.378
lihood+0.370
Neg logit contributions
LLOW-0.524
tten-0.505
��-0.494
 Swordsman-0.487
FACE-0.478
Token
Token ID198
Feature activation-3.81e-01

Pos logit contributions
LLOW+0.142
tten+0.138
��+0.134
 Swordsman+0.131
FACE+0.131
Neg logit contributions
ippers-0.123
ipper-0.120
rones-0.095
lems-0.094
 Carney-0.094
TokenSim
Token ID8890
Feature activation+1.69e-01

Pos logit contributions
ippers+0.336
ipper+0.328
rones+0.276
lems+0.274
 Carney+0.272
Neg logit contributions
LLOW-0.242
tten-0.232
��-0.223
FACE-0.218
 Swordsman-0.215
Tokenpl
Token ID489
Feature activation-3.77e+00

Pos logit contributions
LLOW+0.140
tten+0.138
��+0.134
 Swordsman+0.131
FACE+0.129
Neg logit contributions
ippers-0.115
ipper-0.111
rones-0.086
lihood-0.086
lems-0.086
Tokenorg
Token ID2398
Feature activation-1.66e+00

Pos logit contributions
ippers+3.382
ipper+3.315
lems+2.667
rones+2.667
 Carney+2.637
Neg logit contributions
LLOW-3.064
tten-2.975
��-2.912
 Swordsman-2.821
ADRA-2.793
Token/
Token ID14
Feature activation-1.75e-01

Pos logit contributions
ippers+1.247
ipper+1.218
rones+0.979
lems+0.974
 Carney+0.966
Neg logit contributions
LLOW-1.261
tten-1.228
��-1.206
 Swordsman-1.164
ADRA-1.154
Tokenindex
Token ID9630
Feature activation+1.56e+00

Pos logit contributions
ippers+0.177
ipper+0.174
rones+0.149
lems+0.149
 Carney+0.148
Neg logit contributions
LLOW-0.086
tten-0.083
��-0.080
 Swordsman-0.076
ADRA-0.075
Token.
Token ID13
Feature activation-5.36e+00

Pos logit contributions
LLOW+1.094
tten+1.078
��+1.029
FACE+1.003
 Swordsman+0.998
Neg logit contributions
ippers-1.238
ipper-1.209
 Carney-0.992
rones-0.987
lems-0.987
Tokenphp
Token ID10121
Feature activation-2.39e+00

Pos logit contributions
ippers+3.296
ipper+3.222
rones+2.390
lems+2.375
mast+2.355
Neg logit contributions
LLOW-4.814
tten-4.670
��-4.641
 Swordsman-4.530
ADRA-4.500
Token?
Token ID30
Feature activation-8.15e+00

Pos logit contributions
ippers+1.929
ipper+1.889
rones+1.542
lems+1.534
lihood+1.524
Neg logit contributions
LLOW-1.682
tten-1.637
��-1.608
 Swordsman-1.546
ADRA-1.534
Tokentopic
Token ID26652
Feature activation-1.92e+00

Pos logit contributions
ippers+5.113
ipper+5.023
mast+3.863
service+3.781
lihood+3.765
Neg logit contributions
LLOW-6.914
��-6.657
tten-6.614
 Swordsman-6.610
ADRA-6.577
Token=
Token ID28
Feature activation-2.36e+00

Pos logit contributions
ippers+1.262
ipper+1.229
rones+0.953
lems+0.949
 Carney+0.939
Neg logit contributions
LLOW-1.631
tten-1.595
��-1.565
 Swordsman-1.518
ADRA-1.503
Token28
Token ID2078
Feature activation-2.06e+00

Pos logit contributions
ippers+1.948
ipper+1.910
rones+1.566
lems+1.560
 Carney+1.550
Neg logit contributions
LLOW-1.612
tten-1.567
��-1.538
 Swordsman-1.473
ADRA-1.458
Token18
Token ID1507
Feature activation-2.67e+00

Pos logit contributions
ippers+1.726
ipper+1.691
rones+1.394
lems+1.389
 Carney+1.379
Neg logit contributions
LLOW-1.377
tten-1.338
��-1.309
 Swordsman-1.255
ADRA-1.241
Token48
Token ID2780
Feature activation-1.10e+00

Pos logit contributions
ippers+2.198
ipper+2.158
rones+1.770
lems+1.761
 Carney+1.751
Neg logit contributions
LLOW-1.828
tten-1.777
��-1.751
 Swordsman-1.667
ADRA-1.657
Token/
Token ID14
Feature activation-1.20e+00

Pos logit contributions
ippers+1.671
ipper+1.634
rones+1.308
lems+1.299
 Carney+1.290
Neg logit contributions
LLOW-1.761
tten-1.722
��-1.687
 Swordsman-1.638
ADRA-1.616
Tokenacs
Token ID16436
Feature activation+1.21e+00

Pos logit contributions
ippers+0.905
ipper+0.885
rones+0.712
lems+0.710
 Carney+0.703
Neg logit contributions
LLOW-0.900
tten-0.877
��-0.859
 Swordsman-0.830
ADRA-0.821
Token5
Token ID20
Feature activation-2.01e-01

Pos logit contributions
LLOW+0.924
tten+0.903
��+0.883
 Swordsman+0.846
FACE+0.843
Neg logit contributions
ippers-0.906
ipper-0.882
lems-0.703
rones-0.703
 Carney-0.699
Token/
Token ID14
Feature activation-4.31e-01

Pos logit contributions
ippers+0.145
ipper+0.141
rones+0.113
lems+0.112
 Carney+0.111
Neg logit contributions
LLOW-0.158
tten-0.155
��-0.151
 Swordsman-0.146
FACE-0.145
Tokenprofile
Token ID13317
Feature activation+1.97e+00

Pos logit contributions
ippers+0.329
ipper+0.321
rones+0.259
lems+0.258
 Carney+0.256
Neg logit contributions
LLOW-0.323
tten-0.315
��-0.308
 Swordsman-0.297
FACE-0.294
Token?
Token ID30
Feature activation-8.01e+00

Pos logit contributions
LLOW+1.474
tten+1.437
��+1.396
 Swordsman+1.351
FACE+1.345
Neg logit contributions
ippers-1.491
ipper-1.454
lems-1.167
rones-1.164
 Carney-1.150
Tokenget
Token ID1136
Feature activation-1.80e+00

Pos logit contributions
ippers+5.995
ipper+5.931
mast+4.742
ploy+4.673
rones+4.649
Neg logit contributions
LLOW-5.886
��-5.687
tten-5.636
 Swordsman-5.526
ADRA-5.372
Token=
Token ID28
Feature activation-2.28e+00

Pos logit contributions
ippers+1.343
ipper+1.311
rones+1.052
lems+1.049
 Carney+1.039
Neg logit contributions
LLOW-1.373
tten-1.338
��-1.310
 Swordsman-1.266
ADRA-1.253
TokenNAME
Token ID20608
Feature activation+1.22e+00

Pos logit contributions
ippers+1.797
ipper+1.762
rones+1.427
lems+1.424
mast+1.413
Neg logit contributions
LLOW-1.639
tten-1.595
��-1.568
 Swordsman-1.517
ADRA-1.493
Token,
Token ID11
Feature activation-1.96e+00

Pos logit contributions
LLOW+0.998
tten+0.968
��+0.944
 Swordsman+0.923
FACE+0.921
Neg logit contributions
ippers-0.847
ipper-0.823
lems-0.647
rones-0.645
 Carney-0.629
TokenDP
Token ID6322
Feature activation-1.60e+00

Pos logit contributions
ippers+1.563
ipper+1.532
rones+1.247
lems+1.241
 Carney+1.234
Neg logit contributions
LLOW-1.397
tten-1.360
��-1.332
 Swordsman-1.285
ADRA-1.266
Token were
Token ID547
Feature activation-2.73e+00

Pos logit contributions
ippers+0.307
ipper+0.300
rones+0.238
lems+0.236
 Carney+0.232
Neg logit contributions
LLOW-0.352
tten-0.345
��-0.338
 Swordsman-0.328
FACE-0.324
Token part
Token ID636
Feature activation-2.87e+00

Pos logit contributions
ippers+1.967
ipper+1.916
lems+1.522
 Carney+1.520
rones+1.514
Neg logit contributions
LLOW-2.160
tten-2.087
��-2.050
 Swordsman-1.993
ADRA-1.967
Token of
Token ID286
Feature activation-3.29e+00

Pos logit contributions
ippers+1.990
ipper+1.947
rones+1.523
lems+1.519
 Carney+1.514
Neg logit contributions
LLOW-2.331
tten-2.271
��-2.239
ADRA-2.162
 Swordsman-2.162
Token the
Token ID262
Feature activation-2.68e+00

Pos logit contributions
ippers+2.196
ipper+2.137
lems+1.661
 Carney+1.657
rones+1.644
Neg logit contributions
LLOW-2.761
tten-2.674
��-2.631
 Swordsman-2.571
FACE-2.551
Token messages
Token ID6218
Feature activation-1.76e+00

Pos logit contributions
ippers+1.936
ipper+1.890
lems+1.498
rones+1.496
 Carney+1.488
Neg logit contributions
LLOW-2.114
tten-2.053
��-2.015
 Swordsman-1.951
FACE-1.934
Token Ms
Token ID6997
Feature activation-7.98e+00

Pos logit contributions
ippers+1.270
ipper+1.240
rones+0.982
lems+0.981
 Carney+0.977
Neg logit contributions
LLOW-1.388
tten-1.352
��-1.328
 Swordsman-1.284
ADRA-1.270
Token.
Token ID13
Feature activation-3.49e+00

Pos logit contributions
ippers+5.058
ipper+4.946
 Carney+3.874
lems+3.821
rones+3.740
Neg logit contributions
LLOW-6.761
��-6.754
ADRA-6.617
tten-6.603
��-6.331
Token Lerner
Token ID49750
Feature activation-5.12e+00

Pos logit contributions
ippers+1.895
ipper+1.837
 Carney+1.341
lems+1.339
rones+1.327
Neg logit contributions
LLOW-3.355
tten-3.290
��-3.246
ADRA-3.143
 Swordsman-3.142
Token lost
Token ID2626
Feature activation-3.14e-02

Pos logit contributions
ippers+3.345
ipper+3.270
 Carney+2.514
rones+2.498
lems+2.496
Neg logit contributions
LLOW-4.382
tten-4.268
��-4.200
ADRA-4.068
 Swordsman-4.054
Token in
Token ID287
Feature activation-1.60e+00

Pos logit contributions
ippers+0.023
ipper+0.022
lems+0.018
rones+0.018
 Carney+0.017
Neg logit contributions
LLOW-0.025
tten-0.024
��-0.023
 Swordsman-0.023
FACE-0.023
Token a
Token ID257
Feature activation-2.19e-01

Pos logit contributions
ippers+1.121
ipper+1.094
rones+0.864
lems+0.860
 Carney+0.851
Neg logit contributions
LLOW-1.290
tten-1.260
��-1.235
 Swordsman-1.196
ADRA-1.184
Token Sen
Token ID2311
Feature activation-1.24e+00

Pos logit contributions
ippers+0.368
ipper+0.359
rones+0.285
lems+0.284
mast+0.279
Neg logit contributions
LLOW-0.404
tten-0.395
��-0.385
 Swordsman-0.375
ADRA-0.369
Token.
Token ID13
Feature activation+6.74e-01

Pos logit contributions
ippers+0.932
ipper+0.911
rones+0.732
lems+0.729
 Carney+0.723
Neg logit contributions
LLOW-0.939
tten-0.915
��-0.897
 Swordsman-0.866
ADRA-0.858
Token Cruz
Token ID8742
Feature activation-1.01e+00

Pos logit contributions
LLOW+0.483
tten+0.468
��+0.458
 Swordsman+0.445
FACE+0.441
Neg logit contributions
ippers-0.535
ipper-0.523
rones-0.424
lems-0.423
lihood-0.418
Token was
Token ID373
Feature activation-7.11e-01

Pos logit contributions
ippers+0.735
ipper+0.718
rones+0.571
lems+0.570
 Carney+0.562
Neg logit contributions
LLOW-0.785
tten-0.767
��-0.750
 Swordsman-0.727
FACE-0.718
Token no
Token ID645
Feature activation-2.52e+00

Pos logit contributions
ippers+0.502
ipper+0.489
rones+0.387
lems+0.385
lihood+0.380
Neg logit contributions
LLOW-0.573
tten-0.561
��-0.546
 Swordsman-0.531
FACE-0.528
Token exception
Token ID6631
Feature activation-7.76e+00

Pos logit contributions
ippers+1.590
ipper+1.556
rones+1.185
 Carney+1.179
lems+1.175
Neg logit contributions
LLOW-2.210
tten-2.160
��-2.128
 Swordsman-2.055
ADRA-2.047
Token,
Token ID11
Feature activation-1.24e+00

Pos logit contributions
ippers+4.963
ipper+4.866
 Carney+3.833
lems+3.780
rones+3.759
Neg logit contributions
LLOW-6.462
tten-6.268
ADRA-6.220
��-6.162
FACE-5.972
Token
Token ID447
Feature activation-2.64e-01

Pos logit contributions
ippers+0.925
ipper+0.903
rones+0.724
lems+0.721
 Carney+0.715
Neg logit contributions
LLOW-0.950
tten-0.926
��-0.907
 Swordsman-0.877
ADRA-0.867
Token
Token ID251
Feature activation-1.16e+00

Pos logit contributions
ippers+0.195
ipper+0.191
rones+0.153
lems+0.152
 Carney+0.150
Neg logit contributions
LLOW-0.203
tten-0.198
��-0.195
 Swordsman-0.188
ADRA-0.186
Token a
Token ID257
Feature activation-7.43e-01

Pos logit contributions
ippers+0.858
ipper+0.838
rones+0.669
lems+0.667
 Carney+0.664
Neg logit contributions
LLOW-0.900
tten-0.877
��-0.861
 Swordsman-0.831
ADRA-0.822
Token Cruz
Token ID8742
Feature activation-8.59e-01

Pos logit contributions
ippers+0.529
ipper+0.516
rones+0.408
lems+0.408
 Carney+0.402
Neg logit contributions
LLOW-0.593
tten-0.580
��-0.567
 Swordsman-0.550
FACE-0.544
Token our
Token ID674
Feature activation-2.02e+00

Pos logit contributions
ippers+0.056
ipper+0.055
rones+0.044
lems+0.044
 Carney+0.043
Neg logit contributions
LLOW-0.059
tten-0.058
��-0.056
 Swordsman-0.055
FACE-0.054
Token eyebrows
Token ID26928
Feature activation-3.49e+00

Pos logit contributions
ippers+1.640
ipper+1.605
rones+1.313
lems+1.309
 Carney+1.298
Neg logit contributions
LLOW-1.413
tten-1.374
��-1.344
 Swordsman-1.294
ADRA-1.279
Token and
Token ID290
Feature activation-1.27e+00

Pos logit contributions
ippers+2.492
ipper+2.432
rones+1.931
lems+1.922
 Carney+1.904
Neg logit contributions
LLOW-2.767
tten-2.708
��-2.664
 Swordsman-2.571
ADRA-2.560
Token blew
Token ID17948
Feature activation-3.23e+00

Pos logit contributions
ippers+0.952
ipper+0.932
rones+0.748
lems+0.747
lihood+0.738
Neg logit contributions
LLOW-0.963
tten-0.939
��-0.913
 Swordsman-0.886
FACE-0.879
Token our
Token ID674
Feature activation-2.63e+00

Pos logit contributions
ippers+2.174
ipper+2.115
rones+1.653
lems+1.647
 Carney+1.632
Neg logit contributions
LLOW-2.702
tten-2.639
��-2.597
 Swordsman-2.513
ADRA-2.493
Token minds
Token ID9017
Feature activation-7.38e+00

Pos logit contributions
ippers+1.897
ipper+1.852
rones+1.472
lems+1.466
 Carney+1.452
Neg logit contributions
LLOW-2.074
tten-2.023
��-1.983
 Swordsman-1.919
ADRA-1.898
Token in
Token ID287
Feature activation-1.44e+00

Pos logit contributions
ippers+4.918
ipper+4.772
rones+3.774
 Carney+3.758
lihood+3.746
Neg logit contributions
LLOW-5.976
tten-5.886
��-5.885
ADRA-5.765
 Swordsman-5.580
Token 2014
Token ID1946
Feature activation-2.06e+00

Pos logit contributions
ippers+1.050
ipper+1.026
rones+0.817
lems+0.816
 Carney+0.804
Neg logit contributions
LLOW-1.127
tten-1.100
��-1.076
 Swordsman-1.043
FACE-1.029
Token.
Token ID13
Feature activation-3.79e-01

Pos logit contributions
ippers+1.536
ipper+1.501
rones+1.204
lems+1.199
 Carney+1.188
Neg logit contributions
LLOW-1.570
tten-1.531
��-1.500
 Swordsman-1.449
ADRA-1.434
Token Buck
Token ID13452
Feature activation+2.41e-01

Pos logit contributions
ippers+0.275
ipper+0.268
lems+0.213
rones+0.213
ploy+0.209
Neg logit contributions
LLOW-0.301
tten-0.289
��-0.283
 Swordsman-0.279
FACE-0.275
Tokenle
Token ID293
Feature activation-5.78e-01

Pos logit contributions
LLOW+0.195
tten+0.190
��+0.186
 Swordsman+0.181
FACE+0.179
Neg logit contributions
ippers-0.168
ipper-0.165
rones-0.131
lems-0.129
lihood-0.128
Token.
Token ID13
Feature activation-3.42e-01

Pos logit contributions
ippers+0.372
ipper+0.363
rones+0.291
lems+0.290
 Carney+0.287
Neg logit contributions
LLOW-0.388
tten-0.378
��-0.371
 Swordsman-0.358
ADRA-0.355
Token It
Token ID632
Feature activation-1.53e+00

Pos logit contributions
ippers+0.247
ipper+0.242
rones+0.191
lems+0.191
lihood+0.187
Neg logit contributions
LLOW-0.271
tten-0.263
��-0.257
 Swordsman-0.251
FACE-0.248
Token was
Token ID373
Feature activation+2.55e-01

Pos logit contributions
ippers+1.091
ipper+1.065
rones+0.844
lems+0.842
 Carney+0.831
Neg logit contributions
LLOW-1.214
tten-1.186
��-1.161
 Swordsman-1.126
FACE-1.111
Token just
Token ID655
Feature activation+5.85e-01

Pos logit contributions
LLOW+0.196
tten+0.192
��+0.187
 Swordsman+0.182
FACE+0.180
Neg logit contributions
ippers-0.189
ipper-0.184
rones-0.148
lems-0.147
ploy-0.144
Token one
Token ID530
Feature activation+7.21e-01

Pos logit contributions
LLOW+0.443
tten+0.432
��+0.423
 Swordsman+0.410
FACE+0.404
Neg logit contributions
ippers-0.440
ipper-0.430
rones-0.345
lems-0.345
lihood-0.340
Token example
Token ID1672
Feature activation-7.32e+00

Pos logit contributions
LLOW+0.541
tten+0.531
��+0.513
 Swordsman+0.504
FACE+0.493
Neg logit contributions
ippers-0.549
ipper-0.534
rones-0.434
lems-0.432
mast-0.420
Token of
Token ID286
Feature activation-3.94e+00

Pos logit contributions
ippers+4.465
ipper+4.328
 Carney+3.500
lihood+3.303
mast+3.256
Neg logit contributions
LLOW-6.265
tten-6.058
��-6.022
ADRA-5.891
 Swordsman-5.796
Token Trump
Token ID1301
Feature activation+8.77e-01

Pos logit contributions
ippers+2.783
ipper+2.702
 Carney+2.160
rones+2.135
lems+2.124
Neg logit contributions
LLOW-3.121
tten-3.053
��-3.006
 Swordsman-2.899
ADRA-2.879
Token attempting
Token ID9361
Feature activation+1.44e-01

Pos logit contributions
LLOW+0.664
tten+0.646
��+0.629
 Swordsman+0.610
FACE+0.605
Neg logit contributions
ippers-0.658
ipper-0.645
rones-0.520
lems-0.518
 Carney-0.511
Token to
Token ID284
Feature activation-1.00e+00

Pos logit contributions
LLOW+0.103
tten+0.100
��+0.098
 Swordsman+0.095
ADRA+0.093
Neg logit contributions
ippers-0.114
ipper-0.111
rones-0.091
lems-0.090
 Carney-0.090
Token mend
Token ID47618
Feature activation-9.88e-01

Pos logit contributions
ippers+0.747
ipper+0.730
rones+0.586
lems+0.583
 Carney+0.577
Neg logit contributions
LLOW-0.766
tten-0.749
��-0.731
 Swordsman-0.707
FACE-0.699
Token appeal
Token ID5198
Feature activation-1.66e+00

Pos logit contributions
LLOW+0.405
tten+0.395
��+0.386
 Swordsman+0.373
FACE+0.369
Neg logit contributions
ippers-0.416
ipper-0.406
rones-0.329
lems-0.327
 Carney-0.324
Token to
Token ID284
Feature activation+8.40e-01

Pos logit contributions
ippers+1.231
ipper+1.203
rones+0.963
lems+0.960
 Carney+0.951
Neg logit contributions
LLOW-1.279
tten-1.247
��-1.223
 Swordsman-1.180
ADRA-1.170
Token remain
Token ID3520
Feature activation-2.34e+00

Pos logit contributions
LLOW+0.639
tten+0.628
��+0.598
 Swordsman+0.588
FACE+0.585
Neg logit contributions
ippers-0.620
ipper-0.613
rones-0.495
lems-0.491
lihood-0.486
Token somewhat
Token ID6454
Feature activation-4.06e-01

Pos logit contributions
ippers+1.725
ipper+1.685
rones+1.352
lems+1.340
 Carney+1.326
Neg logit contributions
LLOW-1.814
tten-1.769
��-1.725
 Swordsman-1.674
FACE-1.655
Token un
Token ID555
Feature activation-2.79e-01

Pos logit contributions
ippers+0.309
ipper+0.302
rones+0.245
lems+0.243
 Carney+0.239
Neg logit contributions
LLOW-0.305
tten-0.297
��-0.288
 Swordsman-0.280
FACE-0.277
Tokenspoken
Token ID19842
Feature activation-7.31e+00

Pos logit contributions
ippers+0.210
ipper+0.205
rones+0.166
lems+0.165
 Carney+0.164
Neg logit contributions
LLOW-0.211
tten-0.207
��-0.201
 Swordsman-0.195
ADRA-0.193
Token?
Token ID30
Feature activation-4.18e+00

Pos logit contributions
ippers+5.138
ipper+5.034
lems+3.999
 Carney+3.990
rones+3.971
Neg logit contributions
LLOW-5.732
��-5.584
tten-5.583
ADRA-5.359
 Swordsman-5.275
Token
Token ID198
Feature activation-1.44e+00

Pos logit contributions
ippers+2.741
ipper+2.674
rones+2.076
lems+2.069
 Carney+2.068
Neg logit contributions
LLOW-3.541
tten-3.480
��-3.426
 Swordsman-3.297
ADRA-3.288
Token
Token ID198
Feature activation-1.31e+00

Pos logit contributions
ippers+0.986
ipper+0.961
rones+0.753
lems+0.750
 Carney+0.742
Neg logit contributions
LLOW-1.186
tten-1.157
��-1.130
 Swordsman-1.100
FACE-1.090
TokenPart
Token ID7841
Feature activation+3.76e-01

Pos logit contributions
ippers+1.058
ipper+1.034
rones+0.843
lems+0.840
 Carney+0.836
Neg logit contributions
LLOW-0.926
tten-0.896
��-0.869
FACE-0.842
 Swordsman-0.840
Token of
Token ID286
Feature activation-1.59e+00

Pos logit contributions
LLOW+0.290
tten+0.282
��+0.277
 Swordsman+0.268
ADRA+0.264
Neg logit contributions
ippers-0.277
ipper-0.270
rones-0.217
lems-0.216
 Carney-0.214
Token air
Token ID1633
Feature activation-2.37e+00

Pos logit contributions
ippers+1.382
ipper+1.346
rones+1.063
lems+1.057
 Carney+1.041
Neg logit contributions
LLOW-1.626
tten-1.585
��-1.550
 Swordsman-1.506
FACE-1.490
Tokenspe
Token ID4125
Feature activation-1.12e+00

Pos logit contributions
ippers+1.153
ipper+1.111
rones+0.779
lems+0.767
 Carney+0.760
Neg logit contributions
LLOW-2.423
tten-2.378
��-2.336
 Swordsman-2.279
FACE-2.262
Tokeneds
Token ID5379
Feature activation-9.38e-01

Pos logit contributions
ippers+1.063
ipper+1.044
rones+0.883
lems+0.880
 Carney+0.874
Neg logit contributions
LLOW-0.629
tten-0.608
��-0.590
 Swordsman-0.563
ADRA-0.554
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
ippers+0.713
ipper+0.696
rones+0.563
lems+0.561
 Carney+0.554
Neg logit contributions
LLOW-0.703
tten-0.684
��-0.668
 Swordsman-0.647
FACE-0.639
Token Un
Token ID791
Feature activation-1.74e+00

Pos logit contributions
ippers+0.197
ipper+0.192
rones+0.153
lems+0.153
ploy+0.150
Neg logit contributions
LLOW-0.211
tten-0.202
��-0.198
 Swordsman-0.196
FACE-0.193
Tokenspoken
Token ID19842
Feature activation-7.30e+00

Pos logit contributions
ippers+1.227
ipper+1.197
rones+0.946
lems+0.942
 Carney+0.933
Neg logit contributions
LLOW-1.395
tten-1.361
��-1.336
 Swordsman-1.293
ADRA-1.279
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
ippers+5.067
ipper+4.963
rones+3.879
 Carney+3.860
lems+3.854
Neg logit contributions
LLOW-5.812
tten-5.713
��-5.661
ADRA-5.415
 Swordsman-5.394
Token but
Token ID475
Feature activation-2.32e-01

Pos logit contributions
ippers+0.813
ipper+0.791
rones+0.636
lems+0.635
lihood+0.623
Neg logit contributions
LLOW-0.863
tten-0.836
��-0.817
 Swordsman-0.793
FACE-0.784
Token understood
Token ID7247
Feature activation+9.36e-01

Pos logit contributions
ippers+0.175
ipper+0.171
lems+0.139
rones+0.138
lihood+0.135
Neg logit contributions
LLOW-0.176
tten-0.169
��-0.165
 Swordsman-0.162
FACE-0.159
Token,
Token ID11
Feature activation+1.86e-01

Pos logit contributions
LLOW+0.728
tten+0.705
��+0.684
 Swordsman+0.672
FACE+0.663
Neg logit contributions
ippers-0.677
ipper-0.654
lems-0.529
ploy-0.525
rones-0.523
Token was
Token ID373
Feature activation+8.08e-01

Pos logit contributions
LLOW+0.149
tten+0.144
��+0.140
 Swordsman+0.136
FACE+0.135
Neg logit contributions
ippers-0.133
ipper-0.129
lems-0.103
rones-0.103
ploy-0.103
Token The
Token ID383
Feature activation-1.27e-01

Pos logit contributions
LLOW+0.425
tten+0.408
 Swordsman+0.397
��+0.397
FACE+0.387
Neg logit contributions
ippers-0.395
ipper-0.386
rones-0.306
lems-0.306
lihood-0.301
Token added
Token ID2087
Feature activation-2.10e+00

Pos logit contributions
ippers+0.098
ipper+0.095
rones+0.077
lems+0.077
 Carney+0.076
Neg logit contributions
LLOW-0.094
tten-0.092
��-0.089
 Swordsman-0.087
FACE-0.085
Token Game
Token ID3776
Feature activation-3.92e-01

Pos logit contributions
ippers+1.704
ipper+1.669
rones+1.366
lems+1.360
 Carney+1.349
Neg logit contributions
LLOW-1.467
tten-1.427
��-1.396
 Swordsman-1.341
ADRA-1.329
TokenPad
Token ID26114
Feature activation-3.61e-01

Pos logit contributions
ippers+0.240
ipper+0.233
rones+0.177
lems+0.176
 Carney+0.174
Neg logit contributions
LLOW-0.352
tten-0.345
��-0.338
 Swordsman-0.329
ADRA-0.326
Token features
Token ID3033
Feature activation+2.03e-01

Pos logit contributions
ippers+0.258
ipper+0.250
lems+0.200
rones+0.199
 Carney+0.197
Neg logit contributions
LLOW-0.288
tten-0.281
��-0.274
 Swordsman-0.268
FACE-0.265
Token elicit
Token ID44055
Feature activation-7.22e+00

Pos logit contributions
LLOW+0.157
tten+0.153
��+0.149
 Swordsman+0.145
FACE+0.143
Neg logit contributions
ippers-0.150
ipper-0.146
rones-0.117
lems-0.117
lihood-0.115
Token the
Token ID262
Feature activation-4.73e-01

Pos logit contributions
ippers+4.927
ipper+4.786
rones+3.786
 Carney+3.774
lems+3.755
Neg logit contributions
LLOW-5.753
tten-5.669
��-5.605
 Swordsman-5.383
ADRA-5.356
Token same
Token ID976
Feature activation+5.34e-01

Pos logit contributions
ippers+0.356
ipper+0.348
lems+0.280
rones+0.280
lihood+0.276
Neg logit contributions
LLOW-0.359
tten-0.349
��-0.339
 Swordsman-0.329
FACE-0.326
Token
Token ID564
Feature activation-1.70e-01

Pos logit contributions
LLOW+0.419
tten+0.406
��+0.394
 Swordsman+0.385
FACE+0.382
Neg logit contributions
ippers-0.389
ipper-0.379
rones-0.302
lems-0.300
mast-0.298
Token
Token ID250
Feature activation+4.91e-01

Pos logit contributions
ippers+0.121
ipper+0.118
rones+0.094
lems+0.093
 Carney+0.092
Neg logit contributions
LLOW-0.135
tten-0.132
��-0.131
 Swordsman-0.125
ADRA-0.124
TokenYou
Token ID1639
Feature activation-1.15e+00

Pos logit contributions
LLOW+0.385
tten+0.376
��+0.364
FACE+0.355
 Swordsman+0.351
Neg logit contributions
ippers-0.355
ipper-0.346
rones-0.276
 Carney-0.274
lems-0.274
Token word
Token ID1573
Feature activation+8.09e-01

Pos logit contributions
LLOW+0.531
tten+0.515
��+0.504
 Swordsman+0.493
FACE+0.483
Neg logit contributions
ippers-0.492
ipper-0.478
rones-0.383
lems-0.380
lihood-0.378
Token "
Token ID366
Feature activation+5.40e-01

Pos logit contributions
LLOW+0.666
tten+0.649
��+0.635
 Swordsman+0.616
FACE+0.613
Neg logit contributions
ippers-0.556
ipper-0.540
rones-0.423
lems-0.422
 Carney-0.417
Tokencustom
Token ID23144
Feature activation-8.25e-01

Pos logit contributions
LLOW+0.410
tten+0.402
��+0.390
FACE+0.378
 Swordsman+0.376
Neg logit contributions
ippers-0.405
ipper-0.393
rones-0.317
 Carney-0.315
lihood-0.314
Tokenize
Token ID1096
Feature activation+4.32e-02

Pos logit contributions
ippers+0.700
ipper+0.685
rones+0.566
lems+0.565
 Carney+0.560
Neg logit contributions
LLOW-0.546
tten-0.531
��-0.517
 Swordsman-0.498
ADRA-0.491
Token"
Token ID1
Feature activation-8.94e-01

Pos logit contributions
LLOW+0.027
tten+0.026
��+0.025
 Swordsman+0.024
ADRA+0.024
Neg logit contributions
ippers-0.038
ipper-0.037
rones-0.031
lems-0.031
 Carney-0.031
Token disappear
Token ID10921
Feature activation-7.16e+00

Pos logit contributions
ippers+0.667
ipper+0.651
rones+0.524
lems+0.520
lihood+0.516
Neg logit contributions
LLOW-0.682
tten-0.666
��-0.649
 Swordsman-0.630
FACE-0.623
Token...
Token ID986
Feature activation-1.95e+00

Pos logit contributions
ippers+4.822
ipper+4.735
lems+3.714
rones+3.711
 Carney+3.679
Neg logit contributions
LLOW-5.824
tten-5.687
��-5.684
ADRA-5.470
 Swordsman-5.375
Token until
Token ID1566
Feature activation-1.87e+00

Pos logit contributions
ippers+1.411
ipper+1.377
rones+1.096
lems+1.089
 Carney+1.079
Neg logit contributions
LLOW-1.544
tten-1.510
��-1.474
 Swordsman-1.429
FACE-1.415
Token I
Token ID314
Feature activation-3.11e-01

Pos logit contributions
ippers+1.369
ipper+1.333
rones+1.069
lems+1.067
lihood+1.051
Neg logit contributions
LLOW-1.456
tten-1.429
��-1.392
 Swordsman-1.354
FACE-1.332
Token closed
Token ID4838
Feature activation+1.32e+00

Pos logit contributions
ippers+0.232
ipper+0.226
rones+0.184
lems+0.183
lihood+0.180
Neg logit contributions
LLOW-0.237
tten-0.234
��-0.224
 Swordsman-0.221
FACE-0.216
Token and
Token ID290
Feature activation+9.78e-01

Pos logit contributions
LLOW+0.989
tten+0.964
��+0.942
 Swordsman+0.917
ADRA+0.900
Neg logit contributions
ippers-0.996
ipper-0.970
rones-0.787
lems-0.782
lihood-0.776
Token outgoing
Token ID28181
Feature activation-4.44e+00

Pos logit contributions
ippers+2.289
ipper+2.236
 Carney+1.724
lems+1.721
rones+1.712
Neg logit contributions
LLOW-2.951
tten-2.891
��-2.871
 Swordsman-2.764
ADRA-2.741
Token and
Token ID290
Feature activation-1.36e+00

Pos logit contributions
ippers+2.971
ipper+2.907
lems+2.255
rones+2.247
 Carney+2.246
Neg logit contributions
LLOW-3.704
tten-3.621
��-3.604
ADRA-3.460
 Swordsman-3.458
Token is
Token ID318
Feature activation-1.23e+00

Pos logit contributions
ippers+0.948
ipper+0.921
rones+0.730
lems+0.724
lihood+0.713
Neg logit contributions
LLOW-1.115
tten-1.088
��-1.058
 Swordsman-1.031
FACE-1.028
Token a
Token ID257
Feature activation-9.19e-01

Pos logit contributions
ippers+0.894
ipper+0.869
rones+0.698
lems+0.692
lihood+0.678
Neg logit contributions
LLOW-0.960
tten-0.938
��-0.915
 Swordsman-0.889
FACE-0.883
Token good
Token ID922
Feature activation-5.66e-01

Pos logit contributions
ippers+0.687
ipper+0.663
lems+0.541
rones+0.536
mast+0.524
Neg logit contributions
LLOW-0.697
tten-0.688
��-0.659
 Swordsman-0.650
FACE-0.648
Token conversation
Token ID5273
Feature activation-7.07e+00

Pos logit contributions
ippers+0.411
ipper+0.398
lems+0.320
rones+0.319
ploy+0.313
Neg logit contributions
LLOW-0.442
tten-0.432
��-0.419
 Swordsman-0.413
FACE-0.411
Token starter
Token ID14217
Feature activation-2.13e+00

Pos logit contributions
ipper+4.195
ippers+4.164
mast+3.057
 Carney+3.035
rones+3.019
Neg logit contributions
LLOW-6.348
tten-6.182
��-6.088
 Swordsman-5.874
ADRA-5.821
Token.
Token ID13
Feature activation-8.42e-02

Pos logit contributions
ippers+1.552
ipper+1.516
rones+1.207
lems+1.203
 Carney+1.192
Neg logit contributions
LLOW-1.669
tten-1.629
��-1.596
 Swordsman-1.544
ADRA-1.527
Token<|endoftext|>
Token ID50256
Feature activation+2.38e+00

Pos logit contributions
ippers+0.060
ipper+0.059
rones+0.046
lems+0.046
lihood+0.045
Neg logit contributions
LLOW-0.068
tten-0.065
��-0.064
 Swordsman-0.063
FACE-0.062
TokenWell
Token ID5779
Feature activation+1.48e-01

Pos logit contributions
LLOW+1.585
tten+1.520
��+1.465
FACE+1.447
ATH+1.418
Neg logit contributions
ippers-2.008
ipper-1.968
 Carney-1.634
rones-1.629
lems-1.621
Token,
Token ID11
Feature activation+8.89e-02

Pos logit contributions
LLOW+0.116
tten+0.113
��+0.111
 Swordsman+0.107
FACE+0.106
Neg logit contributions
ippers-0.108
ipper-0.105
rones-0.084
lems-0.084
 Carney-0.083
Token is
Token ID318
Feature activation-5.29e-01

Pos logit contributions
ippers+2.184
ipper+2.128
rones+1.655
lems+1.648
 Carney+1.632
Neg logit contributions
LLOW-2.767
tten-2.703
��-2.654
 Swordsman-2.574
ADRA-2.549
Token just
Token ID655
Feature activation+7.27e-02

Pos logit contributions
ippers+0.382
ipper+0.373
rones+0.297
lems+0.295
mast+0.290
Neg logit contributions
LLOW-0.417
tten-0.409
��-0.400
 Swordsman-0.386
FACE-0.383
Token one
Token ID530
Feature activation+4.43e-01

Pos logit contributions
LLOW+0.058
tten+0.057
��+0.056
 Swordsman+0.054
ADRA+0.053
Neg logit contributions
ippers-0.052
ipper-0.050
rones-0.040
lems-0.040
 Carney-0.039
Token of
Token ID286
Feature activation-5.02e+00

Pos logit contributions
LLOW+0.332
tten+0.326
��+0.315
 Swordsman+0.306
FACE+0.303
Neg logit contributions
ippers-0.339
ipper-0.330
rones-0.268
lems-0.267
mast-0.260
Token many
Token ID867
Feature activation-1.76e+00

Pos logit contributions
ippers+3.830
ipper+3.727
 Carney+3.053
lihood+3.031
lems+3.013
Neg logit contributions
LLOW-3.676
tten-3.557
��-3.498
 Swordsman-3.376
ADRA-3.351
Token instances
Token ID10245
Feature activation-7.05e+00

Pos logit contributions
ippers+1.293
ipper+1.263
rones+1.008
lems+1.005
 Carney+0.997
Neg logit contributions
LLOW-1.367
tten-1.333
��-1.307
 Swordsman-1.263
ADRA-1.250
Token of
Token ID286
Feature activation-1.77e+00

Pos logit contributions
ippers+4.547
ipper+4.369
 Carney+3.553
lihood+3.364
rones+3.354
Neg logit contributions
LLOW-5.892
tten-5.737
��-5.651
FACE-5.401
ADRA-5.384
Token legal
Token ID2742
Feature activation+1.20e-01

Pos logit contributions
ippers+1.312
ipper+1.282
rones+1.026
lems+1.023
 Carney+1.013
Neg logit contributions
LLOW-1.359
tten-1.325
��-1.298
 Swordsman-1.255
ADRA-1.241
Token American
Token ID1605
Feature activation+1.60e+00

Pos logit contributions
LLOW+0.091
tten+0.089
��+0.086
 Swordsman+0.084
ADRA+0.083
Neg logit contributions
ippers-0.090
ipper-0.088
rones-0.071
lems-0.071
lihood-0.071
Token citizens
Token ID4290
Feature activation+6.92e-01

Pos logit contributions
LLOW+1.165
tten+1.145
��+1.104
 Swordsman+1.085
ADRA+1.083
Neg logit contributions
ippers-1.218
ipper-1.195
lems-0.959
rones-0.958
lihood-0.953
Token being
Token ID852
Feature activation-2.87e-01

Pos logit contributions
LLOW+0.476
tten+0.464
��+0.449
 Swordsman+0.436
FACE+0.431
Neg logit contributions
ippers-0.565
ipper-0.554
rones-0.458
lems-0.456
 Carney-0.448
Token being
Token ID852
Feature activation-1.49e+00

Pos logit contributions
ippers+0.235
ipper+0.230
rones+0.185
lems+0.184
 Carney+0.182
Neg logit contributions
LLOW-0.237
tten-0.231
��-0.226
 Swordsman-0.218
FACE-0.216
Token seen
Token ID1775
Feature activation+1.00e+00

Pos logit contributions
ippers+1.218
ipper+1.192
rones+0.973
lems+0.972
 Carney+0.970
Neg logit contributions
LLOW-1.022
tten-0.994
��-0.971
 Swordsman-0.938
ADRA-0.929
Token as
Token ID355
Feature activation-6.54e-01

Pos logit contributions
LLOW+0.735
tten+0.716
��+0.702
 Swordsman+0.676
FACE+0.669
Neg logit contributions
ippers-0.778
ipper-0.760
rones-0.615
lems-0.614
 Carney-0.607
Token the
Token ID262
Feature activation-9.15e-01

Pos logit contributions
ippers+0.469
ipper+0.457
rones+0.365
lems+0.362
lihood+0.357
Neg logit contributions
LLOW-0.520
tten-0.508
��-0.498
 Swordsman-0.481
ADRA-0.477
Token latest
Token ID3452
Feature activation-2.07e+00

Pos logit contributions
ippers+0.772
ipper+0.755
rones+0.626
lems+0.625
lihood+0.616
Neg logit contributions
LLOW-0.610
tten-0.593
��-0.578
 Swordsman-0.556
FACE-0.548
Token instance
Token ID4554
Feature activation-7.02e+00

Pos logit contributions
ippers+1.449
ipper+1.415
rones+1.115
lems+1.111
 Carney+1.102
Neg logit contributions
LLOW-1.676
tten-1.635
��-1.605
 Swordsman-1.554
ADRA-1.538
Token of
Token ID286
Feature activation-2.76e+00

Pos logit contributions
ippers+4.305
ipper+4.183
 Carney+3.329
ploy+3.117
rones+3.097
Neg logit contributions
LLOW-6.023
tten-5.835
��-5.766
 Swordsman-5.641
ADRA-5.598
Token a
Token ID257
Feature activation-8.73e-01

Pos logit contributions
ippers+2.050
ipper+2.002
rones+1.598
lems+1.594
 Carney+1.592
Neg logit contributions
LLOW-2.111
tten-2.056
��-2.023
 Swordsman-1.950
ADRA-1.933
Token new
Token ID649
Feature activation-6.70e-01

Pos logit contributions
ippers+0.660
ipper+0.645
rones+0.520
lems+0.520
lihood+0.511
Neg logit contributions
LLOW-0.659
tten-0.644
��-0.626
 Swordsman-0.608
FACE-0.602
Token mood
Token ID10038
Feature activation-1.54e+00

Pos logit contributions
ippers+0.522
ipper+0.508
rones+0.413
lems+0.411
 Carney+0.403
Neg logit contributions
LLOW-0.494
tten-0.482
��-0.467
 Swordsman-0.455
FACE-0.451
Token of
Token ID286
Feature activation+5.90e-02

Pos logit contributions
ippers+1.073
ipper+1.047
rones+0.824
lems+0.821
 Carney+0.814
Neg logit contributions
LLOW-1.250
tten-1.220
��-1.198
 Swordsman-1.160
ADRA-1.149
Tokencom
Token ID785
Feature activation-1.92e+00

Pos logit contributions
ippers+3.288
ipper+3.237
lems+2.534
mast+2.529
rones+2.515
Neg logit contributions
LLOW-3.895
��-3.884
tten-3.811
ADRA-3.775
 Swordsman-3.665
Token/
Token ID14
Feature activation-2.00e+00

Pos logit contributions
ippers+1.440
ipper+1.407
rones+1.131
lems+1.127
 Carney+1.116
Neg logit contributions
LLOW-1.453
tten-1.418
��-1.393
 Swordsman-1.342
ADRA-1.333
Tokeniv
Token ID452
Feature activation+1.11e+00

Pos logit contributions
ippers+1.630
ipper+1.593
rones+1.312
lems+1.308
mast+1.290
Neg logit contributions
LLOW-1.374
tten-1.344
��-1.316
 Swordsman-1.279
ADRA-1.256
Tokenxx
Token ID5324
Feature activation-2.86e-01

Pos logit contributions
LLOW+0.763
tten+0.744
��+0.723
 Swordsman+0.694
FACE+0.687
Neg logit contributions
ippers-0.919
ipper-0.900
rones-0.738
lems-0.737
 Carney-0.736
Tokenbrand
Token ID17938
Feature activation-1.20e+00

Pos logit contributions
ippers+0.210
ipper+0.205
rones+0.164
lems+0.163
 Carney+0.162
Neg logit contributions
LLOW-0.222
tten-0.217
��-0.212
 Swordsman-0.205
FACE-0.203
Token?
Token ID30
Feature activation-7.01e+00

Pos logit contributions
ippers+0.868
ipper+0.847
rones+0.674
lems+0.671
 Carney+0.665
Neg logit contributions
LLOW-0.940
tten-0.917
��-0.898
 Swordsman-0.869
FACE-0.860
Tokenf
Token ID69
Feature activation-1.04e+00

Pos logit contributions
ippers+4.926
ipper+4.875
mast+3.849
lems+3.763
 Carney+3.704
Neg logit contributions
LLOW-5.409
��-5.269
tten-5.256
 Swordsman-5.142
ADRA-4.998
Tokenref
Token ID5420
Feature activation-3.04e+00

Pos logit contributions
ippers+0.807
ipper+0.791
rones+0.637
lems+0.634
 Carney+0.630
Neg logit contributions
LLOW-0.759
tten-0.740
��-0.727
 Swordsman-0.703
ADRA-0.692
Token=
Token ID28
Feature activation+3.86e-01

Pos logit contributions
ippers+1.969
ipper+1.917
rones+1.481
lems+1.470
 Carney+1.455
Neg logit contributions
LLOW-2.612
tten-2.555
��-2.519
 Swordsman-2.444
ADRA-2.417
Tokents
Token ID912
Feature activation-2.36e-01

Pos logit contributions
LLOW+0.372
tten+0.366
��+0.358
 Swordsman+0.349
FACE+0.347
Neg logit contributions
ippers-0.211
ipper-0.204
rones-0.149
lems-0.147
 Carney-0.145
Token<|endoftext|>
Token ID50256
Feature activation+1.81e+00

Pos logit contributions
ippers+0.172
ipper+0.168
rones+0.134
lems+0.133
 Carney+0.132
Neg logit contributions
LLOW-0.185
tten-0.180
��-0.177
 Swordsman-0.171
FACE-0.170
Token access
Token ID1895
Feature activation+8.86e-01

Pos logit contributions
ippers+0.981
ipper+0.958
rones+0.767
lems+0.763
 Carney+0.757
Neg logit contributions
LLOW-1.026
tten-1.001
��-0.981
 Swordsman-0.948
ADRA-0.938
Token to
Token ID284
Feature activation+5.88e-01

Pos logit contributions
LLOW+0.623
tten+0.608
��+0.594
 Swordsman+0.572
ADRA+0.565
Neg logit contributions
ippers-0.712
ipper-0.697
rones-0.569
lems-0.568
 Carney-0.563
Token calendars
Token ID50215
Feature activation+5.14e-01

Pos logit contributions
LLOW+0.454
tten+0.445
��+0.432
 Swordsman+0.421
FACE+0.417
Neg logit contributions
ippers-0.432
ipper-0.425
lems-0.342
rones-0.336
lihood-0.331
Token.
Token ID13
Feature activation-6.39e-01

Pos logit contributions
LLOW+0.401
tten+0.391
��+0.382
 Swordsman+0.371
FACE+0.367
Neg logit contributions
ippers-0.374
ipper-0.366
lems-0.291
rones-0.290
 Carney-0.287
Token One
Token ID1881
Feature activation-1.03e+00

Pos logit contributions
ippers+0.454
ipper+0.443
rones+0.350
lems+0.349
lihood+0.342
Neg logit contributions
LLOW-0.513
tten-0.497
��-0.487
 Swordsman-0.475
FACE-0.470
Token cabinet
Token ID13447
Feature activation-6.97e+00

Pos logit contributions
ippers+0.767
ipper+0.749
lems+0.603
rones+0.600
 Carney+0.589
Neg logit contributions
LLOW-0.791
tten-0.771
��-0.753
 Swordsman-0.732
FACE-0.722
Token pick
Token ID2298
Feature activation-8.63e-01

Pos logit contributions
ippers+4.529
ipper+4.453
rones+3.460
 Carney+3.447
mast+3.345
Neg logit contributions
LLOW-5.823
tten-5.719
��-5.592
 Swordsman-5.429
FACE-5.379
Token stands
Token ID6296
Feature activation-4.96e-01

Pos logit contributions
ippers+0.623
ipper+0.608
rones+0.484
lems+0.482
 Carney+0.476
Neg logit contributions
LLOW-0.681
tten-0.664
��-0.650
 Swordsman-0.631
FACE-0.621
Token out
Token ID503
Feature activation+2.69e+00

Pos logit contributions
ippers+0.423
ipper+0.414
rones+0.344
lems+0.342
 Carney+0.338
Neg logit contributions
LLOW-0.325
tten-0.315
��-0.305
 Swordsman-0.296
FACE-0.291
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
LLOW+1.968
tten+1.918
��+1.857
 Swordsman+1.826
FACE+1.774
Neg logit contributions
ippers-2.046
ipper-2.006
rones-1.619
lems-1.609
ploy-1.592
Token however
Token ID2158
Feature activation-1.44e+00

Pos logit contributions
ippers+0.760
ipper+0.743
rones+0.595
lems+0.593
lihood+0.582
Neg logit contributions
LLOW-0.811
tten-0.790
��-0.770
 Swordsman-0.752
FACE-0.739
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
ippers+0.715
ipper+0.698
rones+0.557
lems+0.554
 Carney+0.549
Neg logit contributions
LLOW-0.770
tten-0.751
��-0.736
 Swordsman-0.712
ADRA-0.704
Token discover
Token ID7073
Feature activation-2.13e+00

Pos logit contributions
ippers+1.041
ipper+1.015
rones+0.795
lems+0.792
 Carney+0.781
Neg logit contributions
LLOW-1.264
tten-1.237
��-1.209
 Swordsman-1.175
ADRA-1.162
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
ippers+1.555
ipper+1.519
rones+1.208
lems+1.206
 Carney+1.197
Neg logit contributions
LLOW-1.664
tten-1.626
��-1.596
 Swordsman-1.541
ADRA-1.524
Token most
Token ID749
Feature activation-1.23e+00

Pos logit contributions
ippers+0.927
ipper+0.906
rones+0.726
lems+0.724
 Carney+0.718
Neg logit contributions
LLOW-0.946
tten-0.922
��-0.903
 Swordsman-0.873
ADRA-0.863
Token used
Token ID973
Feature activation+8.68e-01

Pos logit contributions
ippers+1.078
ipper+1.056
lems+0.877
rones+0.877
 Carney+0.873
Neg logit contributions
LLOW-0.778
tten-0.755
��-0.738
 Swordsman-0.707
ADRA-0.698
Token Clojure
Token ID43848
Feature activation-6.88e+00

Pos logit contributions
LLOW+0.664
tten+0.647
��+0.627
 Swordsman+0.612
FACE+0.603
Neg logit contributions
ippers-0.647
ipper-0.631
rones-0.508
lems-0.505
 Carney-0.498
Token testing
Token ID4856
Feature activation-2.58e+00

Pos logit contributions
ippers+4.674
ipper+4.567
rones+3.558
lems+3.549
ploy+3.436
Neg logit contributions
LLOW-5.640
tten-5.536
��-5.467
 Swordsman-5.266
FACE-5.214
Token library
Token ID5888
Feature activation-1.20e-01

Pos logit contributions
ippers+1.749
ipper+1.706
rones+1.329
lems+1.327
 Carney+1.312
Neg logit contributions
LLOW-2.142
tten-2.097
��-2.068
 Swordsman-1.990
ADRA-1.978
Token.
Token ID13
Feature activation-1.26e+00

Pos logit contributions
ippers+0.089
ipper+0.087
rones+0.070
lems+0.069
 Carney+0.069
Neg logit contributions
LLOW-0.092
tten-0.090
��-0.087
 Swordsman-0.085
FACE-0.084
Token The
Token ID383
Feature activation-1.46e+00

Pos logit contributions
ippers+0.884
ipper+0.862
rones+0.680
lems+0.677
 Carney+0.669
Neg logit contributions
LLOW-1.022
tten-0.996
��-0.976
 Swordsman-0.948
ADRA-0.936
Token answer
Token ID3280
Feature activation-2.20e+00

Pos logit contributions
ippers+1.077
ipper+1.052
rones+0.841
lems+0.838
 Carney+0.830
Neg logit contributions
LLOW-1.133
tten-1.105
��-1.083
 Swordsman-1.047
ADRA-1.035
Tokenyoutube
Token ID11604
Feature activation-1.10e+00

Pos logit contributions
ippers+2.394
ipper+2.349
rones+1.958
lems+1.952
mast+1.934
Neg logit contributions
LLOW-1.711
tten-1.638
��-1.621
 Swordsman-1.553
ADRA-1.542
Token.
Token ID13
Feature activation-4.00e+00

Pos logit contributions
ippers+0.836
ipper+0.817
rones+0.658
lems+0.655
 Carney+0.649
Neg logit contributions
LLOW-0.828
tten-0.807
��-0.788
 Swordsman-0.763
FACE-0.754
Tokencom
Token ID785
Feature activation-5.43e-01

Pos logit contributions
ippers+2.898
ipper+2.845
rones+2.253
lems+2.242
mast+2.230
Neg logit contributions
LLOW-3.137
��-3.056
tten-3.043
ADRA-2.958
 Swordsman-2.915
Token/
Token ID14
Feature activation-7.78e-01

Pos logit contributions
ippers+0.415
ipper+0.405
rones+0.327
lems+0.326
 Carney+0.323
Neg logit contributions
LLOW-0.406
tten-0.395
��-0.386
 Swordsman-0.373
FACE-0.369
Tokenwatch
Token ID8340
Feature activation-3.77e-01

Pos logit contributions
ippers+0.561
ipper+0.548
rones+0.435
lems+0.434
 Carney+0.427
Neg logit contributions
LLOW-0.614
tten-0.598
��-0.588
 Swordsman-0.571
ADRA-0.562
Token?
Token ID30
Feature activation-6.81e+00

Pos logit contributions
ippers+0.308
ipper+0.301
rones+0.247
lems+0.246
 Carney+0.244
Neg logit contributions
LLOW-0.262
tten-0.255
��-0.250
 Swordsman-0.240
ADRA-0.238
Tokenv
Token ID85
Feature activation-7.55e-01

Pos logit contributions
ippers+4.048
ipper+3.962
mast+2.909
rones+2.893
lems+2.875
Neg logit contributions
LLOW-6.120
��-5.929
tten-5.858
ADRA-5.820
 Swordsman-5.783
Token=
Token ID28
Feature activation+6.94e-01

Pos logit contributions
ippers+0.515
ipper+0.502
lems+0.393
rones+0.392
 Carney+0.391
Neg logit contributions
LLOW-0.624
tten-0.612
��-0.594
 Swordsman-0.577
FACE-0.571
Token2
Token ID17
Feature activation+2.60e-01

Pos logit contributions
LLOW+0.507
tten+0.494
��+0.477
FACE+0.461
 Swordsman+0.460
Neg logit contributions
ippers-0.541
ipper-0.528
rones-0.430
 Carney-0.429
lihood-0.428
Tokeng
Token ID70
Feature activation-9.32e-01

Pos logit contributions
LLOW+0.189
tten+0.184
��+0.178
FACE+0.172
 Swordsman+0.172
Neg logit contributions
ippers-0.204
ipper-0.199
rones-0.162
 Carney-0.162
lems-0.161
Token7
Token ID22
Feature activation+1.95e+00

Pos logit contributions
ippers+0.760
ipper+0.744
rones+0.610
lems+0.607
 Carney+0.604
Neg logit contributions
LLOW-0.649
tten-0.631
��-0.615
 Swordsman-0.593
ADRA-0.586
Token category
Token ID6536
Feature activation-3.51e+00

Pos logit contributions
ippers+0.449
ipper+0.439
rones+0.351
lems+0.350
 Carney+0.346
Neg logit contributions
LLOW-0.468
tten-0.456
��-0.447
 Swordsman-0.432
ADRA-0.427
Token,
Token ID11
Feature activation-9.52e-01

Pos logit contributions
ippers+2.378
ipper+2.320
rones+1.819
 Carney+1.800
lems+1.794
Neg logit contributions
LLOW-2.908
tten-2.838
��-2.786
 Swordsman-2.702
ADRA-2.693
Token where
Token ID810
Feature activation-2.06e+00

Pos logit contributions
ippers+0.666
ipper+0.649
rones+0.512
lems+0.510
 Carney+0.504
Neg logit contributions
LLOW-0.772
tten-0.754
��-0.739
 Swordsman-0.716
ADRA-0.708
Token Emmy
Token ID33953
Feature activation+6.24e-01

Pos logit contributions
ippers+1.558
ipper+1.523
rones+1.226
lems+1.218
 Carney+1.214
Neg logit contributions
LLOW-1.550
tten-1.512
��-1.482
 Swordsman-1.429
ADRA-1.418
Token-
Token ID12
Feature activation-1.64e+00

Pos logit contributions
LLOW+0.477
tten+0.468
��+0.455
 Swordsman+0.442
ADRA+0.439
Neg logit contributions
ippers-0.459
ipper-0.451
lems-0.357
rones-0.356
mast-0.355
Tokenneg
Token ID12480
Feature activation-6.77e+00

Pos logit contributions
ippers+0.989
ipper+0.962
rones+0.723
lems+0.721
 Carney+0.715
Neg logit contributions
LLOW-1.490
tten-1.460
��-1.433
 Swordsman-1.391
FACE-1.381
Tokenlected
Token ID12609
Feature activation-3.15e+00

Pos logit contributions
ippers+4.691
ipper+4.553
rones+3.588
ploy+3.496
lems+3.487
Neg logit contributions
LLOW-5.524
tten-5.295
��-5.281
FACE-5.230
 Swordsman-5.166
Token The
Token ID383
Feature activation-1.37e+00

Pos logit contributions
ippers+2.395
ipper+2.345
rones+1.894
lems+1.877
 Carney+1.873
Neg logit contributions
LLOW-2.355
tten-2.301
��-2.257
ADRA-2.167
 Swordsman-2.165
Token Good
Token ID4599
Feature activation+1.63e+00

Pos logit contributions
ippers+0.973
ipper+0.949
rones+0.750
lems+0.748
lihood+0.737
Neg logit contributions
LLOW-1.109
tten-1.075
��-1.054
 Swordsman-1.028
FACE-1.008
Token Wife
Token ID34188
Feature activation+1.10e+00

Pos logit contributions
LLOW+1.215
tten+1.177
��+1.148
 Swordsman+1.130
FACE+1.102
Neg logit contributions
ippers-1.248
ipper-1.217
lems-0.988
rones-0.977
ploy-0.968
Token was
Token ID373
Feature activation-1.47e+00

Pos logit contributions
LLOW+0.862
tten+0.844
��+0.821
 Swordsman+0.796
FACE+0.784
Neg logit contributions
ippers-0.789
ipper-0.773
lems-0.615
rones-0.609
 Carney-0.605
Token complaint
Token ID8224
Feature activation-1.73e+00

Pos logit contributions
ippers+0.578
ipper+0.564
rones+0.454
lems+0.453
 Carney+0.450
Neg logit contributions
LLOW-0.569
tten-0.553
��-0.542
 Swordsman-0.525
FACE-0.520
Token against
Token ID1028
Feature activation-2.36e+00

Pos logit contributions
ippers+1.214
ipper+1.183
rones+0.934
lems+0.930
 Carney+0.919
Neg logit contributions
LLOW-1.396
tten-1.364
��-1.336
 Swordsman-1.298
FACE-1.281
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
ippers+1.675
ipper+1.635
rones+1.294
lems+1.289
 Carney+1.276
Neg logit contributions
LLOW-1.891
tten-1.846
��-1.810
 Swordsman-1.752
ADRA-1.733
Token club
Token ID3430
Feature activation-1.37e+00

Pos logit contributions
ippers+0.826
ipper+0.807
rones+0.659
lems+0.656
lihood+0.649
Neg logit contributions
LLOW-0.760
tten-0.739
��-0.722
 Swordsman-0.702
FACE-0.688
Token on
Token ID319
Feature activation-9.22e-01

Pos logit contributions
ippers+1.013
ipper+0.990
rones+0.792
lems+0.789
 Carney+0.782
Neg logit contributions
LLOW-1.055
tten-1.029
��-1.007
 Swordsman-0.976
FACE-0.963
Token Oct
Token ID2556
Feature activation-6.77e+00

Pos logit contributions
ippers+0.676
ipper+0.659
lems+0.527
rones+0.525
lihood+0.516
Neg logit contributions
LLOW-0.719
tten-0.702
��-0.686
 Swordsman-0.667
FACE-0.660
Token.
Token ID13
Feature activation-2.01e+00

Pos logit contributions
ippers+4.487
ipper+4.428
rones+3.510
lems+3.445
ploy+3.388
Neg logit contributions
LLOW-5.531
��-5.451
tten-5.427
ADRA-5.263
 Swordsman-5.164
Token 9
Token ID860
Feature activation-2.04e+00

Pos logit contributions
ippers+1.551
ipper+1.516
rones+1.225
lems+1.221
 Carney+1.208
Neg logit contributions
LLOW-1.487
tten-1.447
��-1.414
 Swordsman-1.370
FACE-1.352
Token,
Token ID11
Feature activation-2.15e+00

Pos logit contributions
ippers+1.466
ipper+1.432
rones+1.138
lems+1.133
 Carney+1.122
Neg logit contributions
LLOW-1.621
tten-1.582
��-1.550
 Swordsman-1.499
ADRA-1.485
Token 2015
Token ID1853
Feature activation-1.02e+00

Pos logit contributions
ippers+1.453
ipper+1.416
rones+1.105
lems+1.101
 Carney+1.089
Neg logit contributions
LLOW-1.793
tten-1.752
��-1.719
 Swordsman-1.667
ADRA-1.650
Token.
Token ID13
Feature activation-8.18e-02

Pos logit contributions
ippers+0.763
ipper+0.746
rones+0.599
lems+0.597
 Carney+0.591
Neg logit contributions
LLOW-0.771
tten-0.751
��-0.736
 Swordsman-0.711
ADRA-0.703
Token education
Token ID3707
Feature activation-1.37e+00

Pos logit contributions
LLOW+1.879
tten+1.805
��+1.762
 Swordsman+1.725
ATH+1.678
Neg logit contributions
ippers-2.208
ipper-2.169
lems-1.772
mast-1.760
rones-1.756
Token they
Token ID484
Feature activation-2.24e+00

Pos logit contributions
ippers+0.942
ipper+0.918
rones+0.723
lems+0.719
 Carney+0.710
Neg logit contributions
LLOW-1.127
tten-1.103
��-1.081
 Swordsman-1.044
ADRA-1.037
Token can
Token ID460
Feature activation-6.40e-01

Pos logit contributions
ippers+1.622
ipper+1.584
rones+1.260
lems+1.255
 Carney+1.243
Neg logit contributions
LLOW-1.763
tten-1.720
��-1.685
 Swordsman-1.631
ADRA-1.613
Token and
Token ID290
Feature activation-3.08e-01

Pos logit contributions
ippers+0.451
ipper+0.440
rones+0.347
lems+0.346
 Carney+0.343
Neg logit contributions
LLOW-0.515
tten-0.503
��-0.493
 Swordsman-0.478
ADRA-0.472
Token then
Token ID788
Feature activation+5.72e-01

Pos logit contributions
ippers+0.165
ipper+0.160
rones+0.116
lems+0.115
 Carney+0.113
Neg logit contributions
LLOW-0.299
tten-0.294
��-0.289
 Swordsman-0.282
ADRA-0.279
Token use
Token ID779
Feature activation+4.77e+00

Pos logit contributions
LLOW+0.431
tten+0.419
��+0.410
 Swordsman+0.397
ADRA+0.392
Neg logit contributions
ippers-0.433
ipper-0.423
rones-0.341
lems-0.340
 Carney-0.336
Token it
Token ID340
Feature activation-1.39e-02

Pos logit contributions
LLOW+3.423
tten+3.292
��+3.149
 Swordsman+3.131
FACE+3.115
Neg logit contributions
ippers-3.724
ipper-3.601
lems-2.951
rones-2.918
lihood-2.881
Token to
Token ID284
Feature activation-5.68e-01

Pos logit contributions
ippers+0.011
ipper+0.011
rones+0.009
lems+0.009
 Carney+0.009
Neg logit contributions
LLOW-0.010
tten-0.009
��-0.009
 Swordsman-0.009
FACE-0.009
Token '
Token ID705
Feature activation-1.11e+00

Pos logit contributions
ippers+0.455
ipper+0.445
rones+0.363
lems+0.362
 Carney+0.358
Neg logit contributions
LLOW-0.405
tten-0.393
��-0.381
 Swordsman-0.370
FACE-0.367
Tokenlead
Token ID28230
Feature activation+1.23e+00

Pos logit contributions
ippers+1.079
ipper+1.059
rones+0.899
lems+0.897
 Carney+0.894
Neg logit contributions
LLOW-0.597
tten-0.575
��-0.553
 Swordsman-0.526
FACE-0.524
Token by
Token ID416
Feature activation+2.38e-01

Pos logit contributions
LLOW+1.165
tten+1.132
��+1.108
 Swordsman+1.092
FACE+1.081
Neg logit contributions
ippers-0.702
ipper-0.679
lems-0.496
rones-0.492
mast-0.484
Token.[
Token ID3693
Feature activation-4.23e-02

Pos logit contributions
ippers+0.070
ipper+0.069
rones+0.055
lems+0.055
 Carney+0.054
Neg logit contributions
LLOW-0.070
tten-0.068
��-0.067
 Swordsman-0.064
ADRA-0.064
Token158
Token ID21273
Feature activation+1.41e+00

Pos logit contributions
ippers+0.038
ipper+0.037
rones+0.031
lems+0.031
 Carney+0.030
Neg logit contributions
LLOW-0.026
tten-0.026
��-0.025
 Swordsman-0.024
ADRA-0.024
Token]
Token ID60
Feature activation+3.08e-01

Pos logit contributions
LLOW+0.915
tten+0.888
��+0.866
 Swordsman+0.833
ADRA+0.821
Neg logit contributions
ippers-1.217
ipper-1.193
rones-0.990
lems-0.986
 Carney-0.979
Token
Token ID198
Feature activation+2.32e+00

Pos logit contributions
LLOW+0.241
tten+0.235
��+0.229
 Swordsman+0.224
FACE+0.221
Neg logit contributions
ippers-0.224
ipper-0.218
rones-0.174
lems-0.173
 Carney-0.170
Token
Token ID198
Feature activation+1.80e+00

Pos logit contributions
LLOW+1.753
tten+1.687
FACE+1.609
 Swordsman+1.599
��+1.594
Neg logit contributions
ippers-1.743
ipper-1.693
rones-1.362
lems-1.351
lihood-1.348
TokenSee
Token ID6214
Feature activation+4.85e+00

Pos logit contributions
LLOW+1.107
tten+1.073
��+1.027
FACE+1.008
 Swordsman+0.981
Neg logit contributions
ippers-1.615
ipper-1.579
 Carney-1.322
lems-1.317
rones-1.317
Token also
Token ID635
Feature activation+6.00e-01

Pos logit contributions
LLOW+2.944
tten+2.843
��+2.720
 Swordsman+2.618
FACE+2.596
Neg logit contributions
ippers-4.323
ipper-4.204
lems-3.534
rones-3.513
 Carney-3.476
Token [
Token ID685
Feature activation+2.21e+00

Pos logit contributions
LLOW+0.364
tten+0.353
��+0.345
 Swordsman+0.329
ADRA+0.327
Neg logit contributions
ippers-0.542
ipper-0.532
rones-0.446
lems-0.444
 Carney-0.442
Token edit
Token ID4370
Feature activation+1.16e+00

Pos logit contributions
LLOW+1.164
tten+1.127
��+1.067
 Swordsman+1.026
FACE+1.024
Neg logit contributions
ippers-2.152
ipper-2.106
rones-1.796
 Carney-1.793
lihood-1.786
Token ]
Token ID2361
Feature activation+3.87e+00

Pos logit contributions
LLOW+0.646
tten+0.623
��+0.601
 Swordsman+0.581
FACE+0.568
Neg logit contributions
ippers-1.102
ipper-1.081
rones-0.915
lems-0.911
 Carney-0.904
Token<|endoftext|>
Token ID50256
Feature activation+2.60e+00

Pos logit contributions
LLOW+2.895
tten+2.809
��+2.753
 Swordsman+2.659
FACE+2.633
Neg logit contributions
ippers-2.927
ipper-2.860
rones-2.305
lems-2.279
ploy-2.271
Token northwest
Token ID24821
Feature activation-1.40e+00

Pos logit contributions
LLOW+1.092
tten+1.070
��+1.035
 Swordsman+1.013
FACE+1.001
Neg logit contributions
ippers-1.041
ipper-1.016
rones-0.820
lems-0.818
lihood-0.803
Token corner
Token ID5228
Feature activation+1.02e+00

Pos logit contributions
ippers+0.991
ipper+0.966
rones+0.762
lems+0.757
 Carney+0.754
Neg logit contributions
LLOW-1.126
tten-1.099
��-1.079
 Swordsman-1.043
ADRA-1.037
Token of
Token ID286
Feature activation+4.55e-02

Pos logit contributions
LLOW+0.813
tten+0.793
��+0.777
 Swordsman+0.752
FACE+0.744
Neg logit contributions
ippers-0.734
ipper-0.716
rones-0.569
lems-0.567
 Carney-0.559
Token St
Token ID520
Feature activation+2.94e-01

Pos logit contributions
LLOW+0.035
tten+0.034
��+0.033
 Swordsman+0.032
FACE+0.032
Neg logit contributions
ippers-0.034
ipper-0.033
rones-0.026
lems-0.026
lihood-0.026
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
LLOW+0.223
tten+0.217
��+0.212
 Swordsman+0.205
ADRA+0.203
Neg logit contributions
ippers-0.222
ipper-0.217
rones-0.175
lems-0.174
 Carney-0.173
Token Clair
Token ID48195
Feature activation+4.54e+00

Pos logit contributions
LLOW+1.607
tten+1.559
��+1.523
 Swordsman+1.485
FACE+1.450
Neg logit contributions
ippers-1.965
ipper-1.921
lems-1.590
rones-1.584
lihood-1.568
Token and
Token ID290
Feature activation+5.34e-01

Pos logit contributions
LLOW+3.527
tten+3.419
��+3.307
 Swordsman+3.304
FACE+3.216
Neg logit contributions
ippers-3.257
ipper-3.180
rones-2.554
lems-2.515
lihood-2.511
Token Avenue
Token ID8878
Feature activation+2.29e+00

Pos logit contributions
LLOW+0.413
tten+0.403
��+0.392
 Swordsman+0.383
FACE+0.377
Neg logit contributions
ippers-0.395
ipper-0.385
rones-0.310
lems-0.308
lihood-0.303
Token Road
Token ID5567
Feature activation+2.33e+00

Pos logit contributions
LLOW+1.779
tten+1.739
��+1.687
 Swordsman+1.651
FACE+1.634
Neg logit contributions
ippers-1.676
ipper-1.632
rones-1.310
lems-1.299
lihood-1.286
Token
Token ID198
Feature activation+1.26e+00

Pos logit contributions
LLOW+1.857
tten+1.812
��+1.762
 Swordsman+1.711
FACE+1.692
Neg logit contributions
ippers-1.665
ipper-1.619
rones-1.294
lems-1.282
lihood-1.271
Token
Token ID198
Feature activation+8.18e-01

Pos logit contributions
LLOW+0.993
tten+0.959
��+0.920
FACE+0.911
 Swordsman+0.911
Neg logit contributions
ippers-0.917
ipper-0.893
rones-0.711
lems-0.707
lihood-0.704
Token rooting
Token ID40105
Feature activation+2.07e+00

Pos logit contributions
ippers+0.145
ipper+0.142
rones+0.115
lems+0.114
 Carney+0.112
Neg logit contributions
LLOW-0.142
tten-0.138
��-0.135
 Swordsman-0.131
FACE-0.130
Token for
Token ID329
Feature activation+3.04e-01

Pos logit contributions
LLOW+1.810
tten+1.752
��+1.711
 Swordsman+1.670
FACE+1.658
Neg logit contributions
ippers-1.308
ipper-1.288
rones-0.995
lihood-0.968
 Carney-0.966
Token the
Token ID262
Feature activation+3.25e-01

Pos logit contributions
LLOW+0.220
tten+0.214
��+0.209
 Swordsman+0.203
FACE+0.199
Neg logit contributions
ippers-0.239
ipper-0.234
rones-0.190
lems-0.189
lihood-0.187
Token Democratic
Token ID4390
Feature activation+1.79e+00

Pos logit contributions
LLOW+0.258
tten+0.252
��+0.246
 Swordsman+0.239
FACE+0.236
Neg logit contributions
ippers-0.232
ipper-0.227
rones-0.181
lems-0.180
lihood-0.177
Token presidential
Token ID4787
Feature activation+1.44e+00

Pos logit contributions
LLOW+1.389
tten+1.363
��+1.323
 Swordsman+1.301
FACE+1.270
Neg logit contributions
ippers-1.293
ipper-1.269
rones-1.019
lems-1.013
 Carney-1.004
Token candidate
Token ID4540
Feature activation+4.90e+00

Pos logit contributions
LLOW+1.208
tten+1.190
��+1.158
 Swordsman+1.136
ADRA+1.115
Neg logit contributions
ippers-0.954
ipper-0.932
rones-0.730
lems-0.727
 Carney-0.721
Token say
Token ID910
Feature activation+5.99e-01

Pos logit contributions
LLOW+3.542
tten+3.467
 Swordsman+3.300
FACE+3.296
��+3.261
Neg logit contributions
ippers-3.705
ipper-3.649
rones-2.972
lems-2.938
ploy-2.876
Token their
Token ID511
Feature activation+1.04e+00

Pos logit contributions
LLOW+0.466
tten+0.454
��+0.441
 Swordsman+0.432
FACE+0.426
Neg logit contributions
ippers-0.438
ipper-0.428
rones-0.344
lems-0.340
lihood-0.337
Token accounts
Token ID5504
Feature activation+9.47e-01

Pos logit contributions
LLOW+0.804
tten+0.786
��+0.754
 Swordsman+0.740
FACE+0.738
Neg logit contributions
ippers-0.766
ipper-0.754
rones-0.601
lems-0.594
ploy-0.591
Token on
Token ID319
Feature activation-1.20e-02

Pos logit contributions
LLOW+0.733
tten+0.718
��+0.699
 Swordsman+0.679
FACE+0.676
Neg logit contributions
ippers-0.692
ipper-0.675
lems-0.543
rones-0.543
lihood-0.531
Token the
Token ID262
Feature activation-1.15e+00

Pos logit contributions
ippers+0.010
ipper+0.009
rones+0.008
lems+0.008
lihood+0.007
Neg logit contributions
LLOW-0.009
tten-0.008
��-0.008
 Swordsman-0.008
FACE-0.008
Token handle
Token ID5412
Feature activation-1.84e+00

Pos logit contributions
LLOW+0.624
tten+0.618
��+0.590
 Swordsman+0.579
FACE+0.572
Neg logit contributions
ippers-0.571
ipper-0.553
rones-0.445
lems-0.443
lihood-0.436
Token multiple
Token ID3294
Feature activation-1.79e+00

Pos logit contributions
ippers+1.356
ipper+1.326
rones+1.060
lems+1.056
 Carney+1.048
Neg logit contributions
LLOW-1.417
tten-1.382
��-1.355
 Swordsman-1.309
ADRA-1.295
Token spikes
Token ID27198
Feature activation+2.20e+00

Pos logit contributions
ippers+1.340
ipper+1.310
rones+1.051
lems+1.047
 Carney+1.037
Neg logit contributions
LLOW-1.370
tten-1.336
��-1.309
 Swordsman-1.265
ADRA-1.251
Token in
Token ID287
Feature activation+1.00e-02

Pos logit contributions
LLOW+1.666
tten+1.626
��+1.568
 Swordsman+1.546
FACE+1.510
Neg logit contributions
ippers-1.636
ipper-1.598
rones-1.297
lems-1.293
mast-1.264
Token the
Token ID262
Feature activation+6.76e-01

Pos logit contributions
LLOW+0.008
tten+0.008
��+0.007
 Swordsman+0.007
FACE+0.007
Neg logit contributions
ippers-0.007
ipper-0.007
lems-0.006
rones-0.006
 Carney-0.006
Token angle
Token ID9848
Feature activation+5.50e+00

Pos logit contributions
LLOW+0.521
tten+0.504
��+0.492
 Swordsman+0.479
FACE+0.476
Neg logit contributions
ippers-0.504
ipper-0.487
lems-0.394
rones-0.390
ploy-0.385
Token-
Token ID12
Feature activation+1.34e+00

Pos logit contributions
LLOW+4.115
tten+3.978
��+3.900
 Swordsman+3.783
FACE+3.758
Neg logit contributions
ippers-4.093
ipper-3.941
lems-3.240
rones-3.185
lihood-3.159
Tokenof
Token ID1659
Feature activation-5.12e-02

Pos logit contributions
LLOW+1.008
tten+0.994
��+0.951
FACE+0.928
 Swordsman+0.923
Neg logit contributions
ippers-1.002
ipper-0.974
rones-0.788
 Carney-0.788
lems-0.783
Token-
Token ID12
Feature activation-6.87e-02

Pos logit contributions
ippers+0.034
ipper+0.033
rones+0.026
lems+0.026
 Carney+0.026
Neg logit contributions
LLOW-0.043
tten-0.042
��-0.041
 Swordsman-0.040
FACE-0.040
Tokenattack
Token ID20358
Feature activation-5.13e-01

Pos logit contributions
ippers+0.049
ipper+0.048
rones+0.038
lems+0.038
 Carney+0.038
Neg logit contributions
LLOW-0.054
tten-0.053
��-0.052
 Swordsman-0.050
FACE-0.050
Token data
Token ID1366
Feature activation+2.44e+00

Pos logit contributions
ippers+0.401
ipper+0.392
rones+0.318
lems+0.318
 Carney+0.313
Neg logit contributions
LLOW-0.374
tten-0.364
��-0.356
 Swordsman-0.344
FACE-0.340
Tokenbe
Token ID1350
Feature activation-2.46e+00

Pos logit contributions
ippers+0.326
ipper+0.319
rones+0.258
lems+0.257
 Carney+0.255
Neg logit contributions
LLOW-0.321
tten-0.315
��-0.305
 Swordsman-0.296
FACE-0.293
Token09
Token ID2931
Feature activation+1.25e+00

Pos logit contributions
ippers+1.925
ipper+1.884
rones+1.526
lems+1.523
 Carney+1.504
Neg logit contributions
LLOW-1.791
tten-1.740
��-1.713
 Swordsman-1.647
ADRA-1.628
Tokenc
Token ID66
Feature activation-9.55e-01

Pos logit contributions
LLOW+0.902
tten+0.889
��+0.849
 Swordsman+0.830
FACE+0.822
Neg logit contributions
ippers-0.974
ipper-0.950
rones-0.778
 Carney-0.775
lems-0.771
Token68
Token ID3104
Feature activation+9.13e-01

Pos logit contributions
ippers+0.765
ipper+0.749
rones+0.612
lems+0.610
 Carney+0.605
Neg logit contributions
LLOW-0.676
tten-0.658
��-0.642
 Swordsman-0.620
ADRA-0.612
Tokena
Token ID64
Feature activation+6.42e-01

Pos logit contributions
LLOW+0.660
tten+0.651
��+0.624
 Swordsman+0.609
FACE+0.601
Neg logit contributions
ippers-0.709
ipper-0.693
rones-0.566
 Carney-0.563
lems-0.562
Token410
Token ID33289
Feature activation+2.25e+00

Pos logit contributions
LLOW+0.448
tten+0.437
��+0.422
 Swordsman+0.410
FACE+0.406
Neg logit contributions
ippers-0.518
ipper-0.506
rones-0.416
lems-0.414
 Carney-0.414
Tokenf
Token ID69
Feature activation-2.11e-01

Pos logit contributions
LLOW+1.613
tten+1.600
��+1.514
 Swordsman+1.491
FACE+1.478
Neg logit contributions
ippers-1.731
ipper-1.686
rones-1.390
 Carney-1.382
lems-1.376
Token6
Token ID21
Feature activation+1.80e+00

Pos logit contributions
ippers+0.170
ipper+0.167
rones+0.137
lems+0.136
 Carney+0.136
Neg logit contributions
LLOW-0.147
tten-0.144
��-0.139
 Swordsman-0.135
ADRA-0.133
Tokenbed
Token ID3077
Feature activation+1.57e+00

Pos logit contributions
LLOW+1.372
tten+1.361
��+1.303
 Swordsman+1.276
FACE+1.257
Neg logit contributions
ippers-1.319
ipper-1.285
rones-1.045
 Carney-1.031
lems-1.031
Token15
Token ID1314
Feature activation+2.30e+00

Pos logit contributions
LLOW+1.134
tten+1.119
��+1.066
 Swordsman+1.043
FACE+1.036
Neg logit contributions
ippers-1.220
ipper-1.190
rones-0.974
 Carney-0.972
lems-0.965
Tokenc
Token ID66
Feature activation-5.16e-01

Pos logit contributions
LLOW+1.641
tten+1.630
��+1.537
 Swordsman+1.509
FACE+1.497
Neg logit contributions
ippers-1.777
ipper-1.736
 Carney-1.428
rones-1.424
lems-1.414
Token.
Token ID13
Feature activation+2.78e-01

Pos logit contributions
LLOW+1.306
tten+1.284
��+1.244
 Swordsman+1.227
FACE+1.201
Neg logit contributions
ippers-1.148
ipper-1.115
lems-0.880
rones-0.878
 Carney-0.872
Token
Token ID198
Feature activation+7.56e-01

Pos logit contributions
LLOW+0.215
tten+0.209
��+0.203
 Swordsman+0.202
FACE+0.197
Neg logit contributions
ippers-0.205
ipper-0.201
rones-0.159
lems-0.159
ploy-0.157
Token
Token ID198
Feature activation+3.70e-01

Pos logit contributions
LLOW+0.603
tten+0.585
��+0.563
 Swordsman+0.555
FACE+0.553
Neg logit contributions
ippers-0.540
ipper-0.525
rones-0.417
lems-0.415
 Carney-0.412
TokenHowever
Token ID4864
Feature activation-4.29e-01

Pos logit contributions
LLOW+0.246
tten+0.238
��+0.228
FACE+0.225
ATH+0.220
Neg logit contributions
ippers-0.314
ipper-0.307
 Carney-0.254
rones-0.253
lems-0.252
Token,
Token ID11
Feature activation+7.89e-01

Pos logit contributions
ippers+0.306
ipper+0.299
rones+0.237
lems+0.236
 Carney+0.233
Neg logit contributions
LLOW-0.341
tten-0.335
��-0.328
 Swordsman-0.317
ADRA-0.312
Token now
Token ID783
Feature activation+1.49e+00

Pos logit contributions
LLOW+0.609
tten+0.603
��+0.583
 Swordsman+0.574
FACE+0.554
Neg logit contributions
ippers-0.573
ipper-0.560
rones-0.447
lems-0.446
ploy-0.445
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
LLOW+1.142
tten+1.130
��+1.087
 Swordsman+1.063
FACE+1.038
Neg logit contributions
ippers-1.087
ipper-1.066
lems-0.860
rones-0.853
mast-0.840
Token tide
Token ID20013
Feature activation+3.62e+00

Pos logit contributions
LLOW+1.144
tten+1.125
��+1.095
 Swordsman+1.069
FACE+1.041
Neg logit contributions
ippers-1.068
ipper-1.042
lems-0.829
ploy-0.828
rones-0.826
Token has
Token ID468
Feature activation+6.25e-01

Pos logit contributions
LLOW+2.862
tten+2.804
��+2.753
 Swordsman+2.677
FACE+2.614
Neg logit contributions
ippers-2.535
ipper-2.468
rones-1.950
lems-1.937
lihood-1.932
Token turned
Token ID2900
Feature activation+1.08e+00

Pos logit contributions
LLOW+0.514
tten+0.504
��+0.495
 Swordsman+0.477
FACE+0.472
Neg logit contributions
ippers-0.426
ipper-0.415
rones-0.328
lems-0.323
lihood-0.322
Token again
Token ID757
Feature activation+9.96e-01

Pos logit contributions
LLOW+0.813
tten+0.794
��+0.776
 Swordsman+0.754
FACE+0.740
Neg logit contributions
ippers-0.809
ipper-0.789
rones-0.636
lems-0.627
ploy-0.626
Token?
Token ID30
Feature activation+2.99e-01

Pos logit contributions
LLOW+1.102
tten+1.083
��+1.039
 Swordsman+1.027
ADRA+1.009
Neg logit contributions
ippers-1.164
ipper-1.140
rones-0.923
 Carney-0.914
lems-0.907
Token What
Token ID1867
Feature activation+1.21e+00

Pos logit contributions
LLOW+0.241
tten+0.234
��+0.229
 Swordsman+0.224
FACE+0.221
Neg logit contributions
ippers-0.213
ipper-0.207
rones-0.164
lems-0.163
 Carney-0.161
Token is
Token ID318
Feature activation+2.14e+00

Pos logit contributions
LLOW+0.901
tten+0.882
��+0.850
 Swordsman+0.836
ADRA+0.825
Neg logit contributions
ippers-0.917
ipper-0.897
rones-0.726
 Carney-0.717
lems-0.714
Token it
Token ID340
Feature activation+9.82e-01

Pos logit contributions
LLOW+1.603
tten+1.560
��+1.515
 Swordsman+1.493
FACE+1.467
Neg logit contributions
ippers-1.607
ipper-1.567
lems-1.272
rones-1.268
lihood-1.245
Token?
Token ID30
Feature activation-4.45e-01

Pos logit contributions
LLOW+0.682
tten+0.668
��+0.646
 Swordsman+0.632
FACE+0.622
Neg logit contributions
ippers-0.802
ipper-0.781
rones-0.641
lems-0.638
 Carney-0.632
Token I
Token ID314
Feature activation+6.01e-01

Pos logit contributions
ippers+0.309
ipper+0.301
rones+0.237
lems+0.236
 Carney+0.233
Neg logit contributions
LLOW-0.364
tten-0.355
��-0.348
 Swordsman-0.338
FACE-0.335
Token
Token ID447
Feature activation-3.63e-01

Pos logit contributions
LLOW+0.451
tten+0.440
��+0.426
 Swordsman+0.415
FACE+0.409
Neg logit contributions
ippers-0.458
ipper-0.447
rones-0.362
lems-0.360
 Carney-0.357
Token
Token ID247
Feature activation+5.38e-01

Pos logit contributions
ippers+0.262
ipper+0.256
rones+0.206
lems+0.205
lihood+0.203
Neg logit contributions
LLOW-0.285
tten-0.278
��-0.276
 Swordsman-0.262
FACE-0.260
Tokenll
Token ID297
Feature activation+1.46e+00

Pos logit contributions
LLOW+0.429
tten+0.424
��+0.409
 Swordsman+0.397
FACE+0.394
Neg logit contributions
ippers-0.383
ipper-0.372
rones-0.297
lems-0.293
 Carney-0.292
Token definitely
Token ID4753
Feature activation+9.19e-01

Pos logit contributions
LLOW+1.149
tten+1.128
��+1.090
 Swordsman+1.063
FACE+1.055
Neg logit contributions
ippers-1.062
ipper-1.031
rones-0.828
lems-0.815
lihood-0.814
Token grant
Token ID7264
Feature activation-4.15e-01

Pos logit contributions
LLOW+0.716
tten+0.704
��+0.676
 Swordsman+0.663
FACE+0.655
Neg logit contributions
ippers-0.676
ipper-0.655
rones-0.528
lems-0.522
lihood-0.518
Token arrive
Token ID9240
Feature activation+1.37e+00

Pos logit contributions
ippers+0.326
ipper+0.317
rones+0.254
lems+0.252
 Carney+0.249
Neg logit contributions
LLOW-0.354
tten-0.348
��-0.337
 Swordsman-0.329
FACE-0.323
Token in
Token ID287
Feature activation+1.24e+00

Pos logit contributions
LLOW+1.024
tten+1.011
��+0.968
 Swordsman+0.957
FACE+0.931
Neg logit contributions
ippers-1.038
ipper-1.007
rones-0.815
lihood-0.807
lems-0.806
Token an
Token ID281
Feature activation+1.94e+00

Pos logit contributions
LLOW+0.913
tten+0.897
��+0.868
 Swordsman+0.848
ADRA+0.821
Neg logit contributions
ippers-0.960
ipper-0.934
rones-0.762
lems-0.756
lihood-0.753
Token hour
Token ID1711
Feature activation+2.10e+00

Pos logit contributions
LLOW+1.193
tten+1.168
��+1.149
 Swordsman+1.105
FACE+1.063
Neg logit contributions
ippers-1.743
ipper-1.693
rones-1.426
lems-1.397
lihood-1.394
Token or
Token ID393
Feature activation+1.81e+00

Pos logit contributions
LLOW+1.408
tten+1.368
��+1.331
 Swordsman+1.286
FACE+1.260
Neg logit contributions
ippers-1.749
ipper-1.705
rones-1.403
lems-1.392
 Carney-1.391
Token two
Token ID734
Feature activation+3.97e+00

Pos logit contributions
LLOW+1.302
tten+1.274
��+1.234
 Swordsman+1.211
FACE+1.183
Neg logit contributions
ippers-1.415
ipper-1.376
rones-1.125
lems-1.113
 Carney-1.099
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
LLOW+2.575
tten+2.489
��+2.415
 Swordsman+2.331
FACE+2.287
Neg logit contributions
ippers-3.376
ipper-3.285
rones-2.751
lihood-2.692
 Carney-2.686
Token The
Token ID383
Feature activation+1.09e+00

Pos logit contributions
LLOW+1.100
tten+1.050
��+1.029
 Swordsman+1.024
FACE+1.002
Neg logit contributions
ippers-1.073
ipper-1.046
rones-0.845
lems-0.836
ploy-0.822
Token outside
Token ID2354
Feature activation+4.69e-01

Pos logit contributions
LLOW+0.816
tten+0.803
��+0.776
 Swordsman+0.767
FACE+0.739
Neg logit contributions
ippers-0.825
ipper-0.807
rones-0.651
lihood-0.644
lems-0.642
Token is
Token ID318
Feature activation+5.80e-01

Pos logit contributions
LLOW+0.360
tten+0.353
��+0.343
 Swordsman+0.337
FACE+0.331
Neg logit contributions
ippers-0.345
ipper-0.340
rones-0.273
lems-0.270
ploy-0.267
Token becoming
Token ID5033
Feature activation+1.03e+00

Pos logit contributions
LLOW+0.438
tten+0.435
��+0.422
 Swordsman+0.407
FACE+0.403
Neg logit contributions
ippers-0.436
ipper-0.426
rones-0.344
lems-0.339
lihood-0.335
Token
Token ID198
Feature activation-1.32e-01

Pos logit contributions
LLOW+0.176
tten+0.171
��+0.165
 Swordsman+0.162
FACE+0.161
Neg logit contributions
ippers-0.153
ipper-0.149
rones-0.118
lems-0.117
lihood-0.116
Token"
Token ID1
Feature activation-1.36e+00

Pos logit contributions
ippers+0.112
ipper+0.109
rones+0.090
lems+0.090
 Carney+0.089
Neg logit contributions
LLOW-0.088
tten-0.085
��-0.083
FACE-0.080
ADRA-0.079
TokenFor
Token ID1890
Feature activation+3.07e+00

Pos logit contributions
ippers+1.133
ipper+1.110
rones+0.911
lems+0.909
 Carney+0.900
Neg logit contributions
LLOW-0.931
tten-0.901
��-0.881
 Swordsman-0.847
FACE-0.840
Token all
Token ID477
Feature activation+1.91e+00

Pos logit contributions
LLOW+2.312
tten+2.286
��+2.222
ADRA+2.139
 Swordsman+2.127
Neg logit contributions
ippers-2.274
ipper-2.225
rones-1.777
lems-1.768
mast-1.748
Token the
Token ID262
Feature activation+9.77e-01

Pos logit contributions
LLOW+1.495
tten+1.463
��+1.428
 Swordsman+1.383
ADRA+1.375
Neg logit contributions
ippers-1.379
ipper-1.348
rones-1.076
lems-1.075
lihood-1.050
Token pomp
Token ID49435
Feature activation+2.65e+00

Pos logit contributions
LLOW+0.724
tten+0.710
��+0.693
 Swordsman+0.670
FACE+0.665
Neg logit contributions
ippers-0.746
ipper-0.730
rones-0.590
lems-0.588
lihood-0.574
Token and
Token ID290
Feature activation-3.25e-01

Pos logit contributions
LLOW+2.052
tten+1.997
��+1.957
 Swordsman+1.888
FACE+1.884
Neg logit contributions
ippers-1.920
ipper-1.877
lems-1.496
rones-1.474
lihood-1.465
Token ceremony
Token ID10542
Feature activation+1.03e+00

Pos logit contributions
ippers+0.242
ipper+0.237
rones+0.190
lems+0.189
 Carney+0.187
Neg logit contributions
LLOW-0.248
tten-0.242
��-0.236
 Swordsman-0.229
FACE-0.227
Token,
Token ID11
Feature activation+1.58e+00

Pos logit contributions
LLOW+0.797
tten+0.778
��+0.761
 Swordsman+0.737
FACE+0.732
Neg logit contributions
ippers-0.749
ipper-0.732
lems-0.587
rones-0.584
lihood-0.571
Token nothing
Token ID2147
Feature activation+2.42e+00

Pos logit contributions
LLOW+1.297
tten+1.265
��+1.234
 Swordsman+1.205
FACE+1.192
Neg logit contributions
ippers-1.082
ipper-1.054
lems-0.832
rones-0.823
lihood-0.804
Token in
Token ID287
Feature activation+7.03e-01

Pos logit contributions
LLOW+1.847
tten+1.801
��+1.769
 Swordsman+1.725
FACE+1.701
Neg logit contributions
ippers-1.810
ipper-1.767
lems-1.409
rones-1.395
mast-1.374
Tokencar
Token ID7718
Feature activation-3.45e+00

Pos logit contributions
LLOW+1.272
tten+1.265
��+1.217
FACE+1.199
 Swordsman+1.190
Neg logit contributions
ippers-0.735
ipper-0.713
lihood-0.516
rones-0.510
lems-0.506
Tokenibe
Token ID32438
Feature activation-2.22e+00

Pos logit contributions
ippers+1.100
ipper+1.042
rones+0.539
lems+0.535
 Carney+0.513
Neg logit contributions
LLOW-4.127
tten-4.052
��-4.009
 Swordsman-3.912
ADRA-3.899
Token deal
Token ID1730
Feature activation-1.25e+00

Pos logit contributions
ippers+1.246
ipper+1.207
rones+0.888
lems+0.884
 Carney+0.865
Neg logit contributions
LLOW-2.105
tten-2.068
��-2.027
 Swordsman-1.977
ADRA-1.957
Token would
Token ID561
Feature activation-2.14e+00

Pos logit contributions
ippers+0.875
ipper+0.854
lems+0.672
rones+0.669
ploy+0.655
Neg logit contributions
LLOW-1.009
tten-0.992
��-0.969
 Swordsman-0.938
FACE-0.927
Token help
Token ID1037
Feature activation+2.10e-01

Pos logit contributions
ippers+1.536
ipper+1.499
rones+1.194
lems+1.189
 Carney+1.167
Neg logit contributions
LLOW-1.697
tten-1.666
��-1.618
 Swordsman-1.572
FACE-1.557
Token lower
Token ID2793
Feature activation-2.50e+00

Pos logit contributions
LLOW+0.163
tten+0.160
��+0.157
 Swordsman+0.151
ADRA+0.150
Neg logit contributions
ippers-0.153
ipper-0.150
rones-0.120
lems-0.119
mast-0.118
Token and
Token ID290
Feature activation-1.21e+00

Pos logit contributions
ippers+1.796
ipper+1.752
rones+1.391
lems+1.385
 Carney+1.373
Neg logit contributions
LLOW-1.983
tten-1.935
��-1.897
 Swordsman-1.836
ADRA-1.816
Token stabilize
Token ID32411
Feature activation-1.12e+00

Pos logit contributions
ippers+0.880
ipper+0.862
lems+0.686
rones+0.681
 Carney+0.674
Neg logit contributions
LLOW-0.942
tten-0.923
��-0.905
 Swordsman-0.871
FACE-0.859
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
ippers+0.818
ipper+0.800
rones+0.639
lems+0.637
 Carney+0.625
Neg logit contributions
LLOW-0.878
tten-0.858
��-0.841
 Swordsman-0.811
FACE-0.801
Token cost
Token ID1575
Feature activation+2.19e+00

Pos logit contributions
ippers+0.750
ipper+0.732
rones+0.581
lems+0.580
mast+0.569
Neg logit contributions
LLOW-0.838
tten-0.818
��-0.804
 Swordsman-0.776
FACE-0.765
Token of
Token ID286
Feature activation-3.13e-01

Pos logit contributions
LLOW+1.628
tten+1.586
��+1.549
 Swordsman+1.495
FACE+1.493
Neg logit contributions
ippers-1.654
ipper-1.618
rones-1.308
lems-1.307
mast-1.288
Token by
Token ID416
Feature activation-1.31e+00

Pos logit contributions
ippers+0.093
ipper+0.090
rones+0.069
lems+0.068
 Carney+0.067
Neg logit contributions
LLOW-0.137
tten-0.133
��-0.131
 Swordsman-0.128
FACE-0.126
Token trying
Token ID2111
Feature activation+2.89e+00

Pos logit contributions
ippers+0.999
ipper+0.977
rones+0.789
lems+0.784
 Carney+0.775
Neg logit contributions
LLOW-0.987
tten-0.961
��-0.939
 Swordsman-0.909
FACE-0.897
Token to
Token ID284
Feature activation-2.10e-01

Pos logit contributions
LLOW+1.997
tten+1.943
��+1.900
 Swordsman+1.833
FACE+1.815
Neg logit contributions
ippers-2.355
ipper-2.308
rones-1.892
 Carney-1.869
lems-1.869
Token reconcile
Token ID33570
Feature activation-2.32e+00

Pos logit contributions
ippers+0.155
ipper+0.152
rones+0.123
lems+0.121
 Carney+0.120
Neg logit contributions
LLOW-0.163
tten-0.159
��-0.153
 Swordsman-0.150
FACE-0.149
Token that
Token ID326
Feature activation-2.74e-01

Pos logit contributions
ippers+1.631
ipper+1.594
rones+1.259
lems+1.252
 Carney+1.243
Neg logit contributions
LLOW-1.864
tten-1.820
��-1.788
 Swordsman-1.725
ADRA-1.713
Token with
Token ID351
Feature activation-4.30e-01

Pos logit contributions
ippers+0.198
ipper+0.193
rones+0.154
lems+0.153
 Carney+0.151
Neg logit contributions
LLOW-0.216
tten-0.211
��-0.205
 Swordsman-0.200
FACE-0.198
Token his
Token ID465
Feature activation+9.34e-01

Pos logit contributions
ippers+0.326
ipper+0.319
rones+0.257
lems+0.256
 Carney+0.253
Neg logit contributions
LLOW-0.323
tten-0.315
��-0.308
 Swordsman-0.298
FACE-0.294
Token religion
Token ID5737
Feature activation-1.26e+00

Pos logit contributions
LLOW+0.681
tten+0.665
��+0.642
 Swordsman+0.626
FACE+0.616
Neg logit contributions
ippers-0.731
ipper-0.714
rones-0.582
lems-0.577
 Carney-0.571
Token,
Token ID11
Feature activation-3.13e-02

Pos logit contributions
ippers+0.901
ipper+0.880
rones+0.698
lems+0.694
 Carney+0.688
Neg logit contributions
LLOW-1.003
tten-0.980
��-0.961
 Swordsman-0.929
ADRA-0.920
Token culture
Token ID3968
Feature activation-2.99e+00

Pos logit contributions
ippers+0.023
ipper+0.023
rones+0.018
lems+0.018
ploy+0.018
Neg logit contributions
LLOW-0.024
tten-0.023
��-0.023
 Swordsman-0.022
FACE-0.022
Token,
Token ID11
Feature activation+5.18e-01

Pos logit contributions
ippers+2.105
ipper+2.061
rones+1.641
lems+1.633
 Carney+1.612
Neg logit contributions
LLOW-2.376
tten-2.328
��-2.285
 Swordsman-2.203
FACE-2.185
Token a
Token ID257
Feature activation+4.91e-01

Pos logit contributions
LLOW+1.612
tten+1.598
��+1.530
 Swordsman+1.509
FACE+1.479
Neg logit contributions
ippers-1.640
ipper-1.585
rones-1.281
lems-1.279
ploy-1.258
Token very
Token ID845
Feature activation-7.98e-01

Pos logit contributions
LLOW+0.374
tten+0.370
��+0.355
 Swordsman+0.349
FACE+0.342
Neg logit contributions
ippers-0.367
ipper-0.355
lems-0.287
rones-0.287
lihood-0.281
Token interesting
Token ID3499
Feature activation+9.91e-01

Pos logit contributions
ippers+0.593
ipper+0.576
rones+0.465
lems+0.460
lihood+0.454
Neg logit contributions
LLOW-0.614
tten-0.602
��-0.583
 Swordsman-0.569
FACE-0.562
Token session
Token ID6246
Feature activation-2.43e+00

Pos logit contributions
LLOW+0.703
tten+0.692
��+0.666
 Swordsman+0.650
FACE+0.641
Neg logit contributions
ippers-0.793
ipper-0.769
rones-0.634
lems-0.631
ploy-0.622
Token to
Token ID284
Feature activation+8.38e-01

Pos logit contributions
ippers+1.730
ipper+1.694
rones+1.339
 Carney+1.331
lems+1.330
Neg logit contributions
LLOW-1.928
tten-1.879
��-1.849
 Swordsman-1.783
ADRA-1.779
Token say
Token ID910
Feature activation-3.66e-01

Pos logit contributions
LLOW+0.671
tten+0.660
��+0.629
 Swordsman+0.619
FACE+0.613
Neg logit contributions
ippers-0.593
ipper-0.579
rones-0.465
lems-0.463
lihood-0.460
Token the
Token ID262
Feature activation+7.64e-01

Pos logit contributions
ippers+0.275
ipper+0.268
rones+0.216
lems+0.215
 Carney+0.212
Neg logit contributions
LLOW-0.278
tten-0.271
��-0.265
 Swordsman-0.257
FACE-0.254
Token least
Token ID1551
Feature activation-1.72e+00

Pos logit contributions
LLOW+0.565
tten+0.551
��+0.536
 Swordsman+0.517
FACE+0.507
Neg logit contributions
ippers-0.587
ipper-0.571
rones-0.466
lems-0.462
lihood-0.461
Token.
Token ID13
Feature activation-9.00e-02

Pos logit contributions
ippers+1.249
ipper+1.222
rones+0.974
lems+0.969
 Carney+0.967
Neg logit contributions
LLOW-1.341
tten-1.309
��-1.287
 Swordsman-1.241
ADRA-1.235
Token I
Token ID314
Feature activation+3.33e-02

Pos logit contributions
ippers+0.067
ipper+0.066
rones+0.052
lems+0.052
ploy+0.051
Neg logit contributions
LLOW-0.069
tten-0.067
��-0.066
 Swordsman-0.064
FACE-0.063
Token consider
Token ID2074
Feature activation+6.17e-01

Pos logit contributions
LLOW+0.026
tten+0.025
��+0.024
 Swordsman+0.024
FACE+0.024
Neg logit contributions
ippers-0.024
ipper-0.024
lems-0.019
rones-0.019
lihood-0.019
Token Committee
Token ID4606
Feature activation-3.42e+00

Pos logit contributions
LLOW+0.697
tten+0.669
��+0.658
 Swordsman+0.643
FACE+0.627
Neg logit contributions
ippers-0.757
ipper-0.737
rones-0.602
lems-0.600
lihood-0.591
Token.
Token ID13
Feature activation+1.63e+00

Pos logit contributions
ippers+2.364
ipper+2.304
 Carney+1.815
rones+1.805
lems+1.799
Neg logit contributions
LLOW-2.769
tten-2.698
��-2.647
 Swordsman-2.571
ADRA-2.565
Token F
Token ID376
Feature activation-3.65e-01

Pos logit contributions
LLOW+1.241
tten+1.193
��+1.169
 Swordsman+1.150
FACE+1.130
Neg logit contributions
ippers-1.232
ipper-1.205
rones-0.970
lems-0.968
ploy-0.950
Tokeness
Token ID408
Feature activation-4.59e-01

Pos logit contributions
ippers+0.390
ipper+0.384
rones+0.332
lems+0.331
ploy+0.326
Neg logit contributions
LLOW-0.163
tten-0.154
��-0.152
 Swordsman-0.141
ADRA-0.141
Tokenend
Token ID437
Feature activation-2.77e+00

Pos logit contributions
ippers+0.397
ipper+0.389
rones+0.323
lems+0.322
 Carney+0.320
Neg logit contributions
LLOW-0.295
tten-0.287
��-0.279
 Swordsman-0.268
FACE-0.265
Tokenen
Token ID268
Feature activation-1.42e+00

Pos logit contributions
ippers+1.780
ipper+1.735
rones+1.327
lems+1.316
mast+1.309
Neg logit contributions
LLOW-2.417
��-2.345
tten-2.314
ADRA-2.291
 Swordsman-2.260
Token took
Token ID1718
Feature activation-1.55e-01

Pos logit contributions
ippers+1.037
ipper+1.012
rones+0.808
lems+0.805
 Carney+0.797
Neg logit contributions
LLOW-1.102
tten-1.075
��-1.053
 Swordsman-1.019
ADRA-1.007
Token no
Token ID645
Feature activation-6.87e-01

Pos logit contributions
ippers+0.115
ipper+0.112
rones+0.090
lems+0.089
 Carney+0.089
Neg logit contributions
LLOW-0.120
tten-0.117
��-0.115
 Swordsman-0.111
ADRA-0.110
Token immediate
Token ID7103
Feature activation-2.21e+00

Pos logit contributions
ippers+0.557
ipper+0.543
rones+0.444
lems+0.442
lihood+0.437
Neg logit contributions
LLOW-0.482
tten-0.468
��-0.456
 Swordsman-0.443
FACE-0.437
Token action
Token ID2223
Feature activation-1.86e+00

Pos logit contributions
ippers+1.802
ipper+1.768
rones+1.450
lems+1.446
 Carney+1.439
Neg logit contributions
LLOW-1.524
tten-1.484
��-1.452
 Swordsman-1.394
ADRA-1.381
Token,
Token ID11
Feature activation-3.10e-03

Pos logit contributions
ippers+1.313
ipper+1.285
lems+1.013
rones+1.011
 Carney+1.008
Neg logit contributions
LLOW-1.500
tten-1.458
��-1.436
ADRA-1.384
 Swordsman-1.384
Token.
Token ID13
Feature activation+3.60e-01

Pos logit contributions
ippers+1.001
ipper+0.979
rones+0.788
lems+0.785
 Carney+0.778
Neg logit contributions
LLOW-0.996
tten-0.971
��-0.950
 Swordsman-0.918
ADRA-0.907
Token
Token ID198
Feature activation-6.69e-01

Pos logit contributions
LLOW+0.280
tten+0.271
��+0.265
 Swordsman+0.259
FACE+0.255
Neg logit contributions
ippers-0.265
ipper-0.258
rones-0.206
lems-0.206
mast-0.202
Token
Token ID198
Feature activation-7.59e-01

Pos logit contributions
ippers+0.464
ipper+0.452
rones+0.355
lems+0.353
 Carney+0.350
Neg logit contributions
LLOW-0.548
tten-0.534
��-0.520
 Swordsman-0.507
FACE-0.504
TokenImpro
Token ID23028
Feature activation+1.14e+00

Pos logit contributions
ippers+0.691
ipper+0.678
rones+0.568
lems+0.567
 Carney+0.563
Neg logit contributions
LLOW-0.457
tten-0.441
��-0.429
 Swordsman-0.409
FACE-0.408
Tokenving
Token ID1075
Feature activation+1.27e+00

Pos logit contributions
LLOW+0.772
tten+0.757
��+0.735
 Swordsman+0.703
FACE+0.697
Neg logit contributions
ippers-0.946
ipper-0.926
rones-0.761
lems-0.760
 Carney-0.756
Token delivery
Token ID7585
Feature activation-1.57e+00

Pos logit contributions
LLOW+0.963
tten+0.942
��+0.916
 Swordsman+0.887
FACE+0.880
Neg logit contributions
ippers-0.943
ipper-0.920
rones-0.739
lems-0.736
 Carney-0.724
Token of
Token ID286
Feature activation-1.79e-01

Pos logit contributions
ippers+1.132
ipper+1.105
rones+0.878
lems+0.877
 Carney+0.866
Neg logit contributions
LLOW-1.243
tten-1.213
��-1.187
 Swordsman-1.150
FACE-1.137
Token services
Token ID2594
Feature activation+2.81e+00

Pos logit contributions
ippers+0.127
ipper+0.124
rones+0.098
lems+0.098
 Carney+0.097
Neg logit contributions
LLOW-0.143
tten-0.139
��-0.136
 Swordsman-0.132
FACE-0.130
Token to
Token ID284
Feature activation-3.39e-01

Pos logit contributions
LLOW+2.152
tten+2.128
��+2.042
 Swordsman+2.020
FACE+1.969
Neg logit contributions
ippers-2.028
ipper-1.975
rones-1.588
lems-1.582
lihood-1.568
Token the
Token ID262
Feature activation+4.63e-01

Pos logit contributions
ippers+0.258
ipper+0.254
rones+0.205
lems+0.203
 Carney+0.202
Neg logit contributions
LLOW-0.253
tten-0.248
��-0.240
 Swordsman-0.233
ADRA-0.231
Token stakeholders
Token ID26138
Feature activation+1.19e+00

Pos logit contributions
LLOW+0.312
tten+0.305
��+0.294
 Swordsman+0.283
FACE+0.280
Neg logit contributions
ippers-0.387
ipper-0.380
rones-0.316
lems-0.311
 Carney-0.308
Token
Token ID247
Feature activation-2.53e-02

Pos logit contributions
LLOW+0.328
��+0.320
tten+0.319
ADRA+0.300
 Swordsman+0.299
Neg logit contributions
ippers-0.318
ipper-0.310
rones-0.252
lihood-0.251
lems-0.250
Tokent
Token ID83
Feature activation+1.26e+00

Pos logit contributions
ippers+0.019
ipper+0.018
rones+0.015
lihood+0.015
lems+0.015
Neg logit contributions
tten-0.019
LLOW-0.019
��-0.018
FACE-0.018
 Swordsman-0.018
Token one
Token ID530
Feature activation+1.81e+00

Pos logit contributions
LLOW+0.964
tten+0.939
��+0.915
 Swordsman+0.887
ADRA+0.877
Neg logit contributions
ippers-0.932
ipper-0.911
rones-0.734
lems-0.733
mast-0.720
Token of
Token ID286
Feature activation-3.49e+00

Pos logit contributions
LLOW+1.360
tten+1.329
��+1.284
 Swordsman+1.260
ADRA+1.243
Neg logit contributions
ippers-1.372
ipper-1.334
lems-1.096
rones-1.085
lihood-1.065
Token the
Token ID262
Feature activation-2.65e+00

Pos logit contributions
ippers+2.443
ipper+2.385
rones+1.878
 Carney+1.878
lems+1.865
Neg logit contributions
LLOW-2.811
tten-2.741
��-2.694
 Swordsman-2.615
ADRA-2.570
Token bureau
Token ID10583
Feature activation-4.10e+00

Pos logit contributions
ippers+2.010
ipper+1.963
rones+1.581
lems+1.574
 Carney+1.563
Neg logit contributions
LLOW-1.989
tten-1.939
��-1.899
 Swordsman-1.833
ADRA-1.813
Token
Token ID447
Feature activation+7.19e-01

Pos logit contributions
ippers+2.900
ipper+2.814
rones+2.244
lems+2.235
 Carney+2.186
Neg logit contributions
LLOW-3.286
tten-3.194
��-3.162
 Swordsman-3.057
FACE-3.012
Token
Token ID247
Feature activation-1.06e+00

Pos logit contributions
LLOW+0.553
��+0.539
tten+0.537
ADRA+0.505
 Swordsman+0.504
Neg logit contributions
ippers-0.527
ipper-0.519
lihood-0.417
rones-0.415
lems-0.412
Tokens
Token ID82
Feature activation-9.84e-01

Pos logit contributions
ippers+0.647
ipper+0.632
rones+0.480
lems+0.474
 Carney+0.474
Neg logit contributions
LLOW-0.947
tten-0.935
��-0.908
 Swordsman-0.883
FACE-0.878
Token many
Token ID867
Feature activation-1.26e+00

Pos logit contributions
ippers+0.700
ipper+0.686
rones+0.544
lems+0.541
 Carney+0.536
Neg logit contributions
LLOW-0.784
tten-0.766
��-0.748
 Swordsman-0.726
ADRA-0.718
Token tech
Token ID7261
Feature activation-1.01e+00

Pos logit contributions
ippers+0.908
ipper+0.888
rones+0.706
lems+0.703
 Carney+0.695
Neg logit contributions
LLOW-0.996
tten-0.972
��-0.950
 Swordsman-0.922
ADRA-0.912
Token this
Token ID428
Feature activation+4.20e-01

Pos logit contributions
ippers+0.369
ipper+0.360
rones+0.284
lems+0.283
 Carney+0.279
Neg logit contributions
LLOW-0.429
tten-0.417
��-0.409
 Swordsman-0.397
FACE-0.393
Token all
Token ID477
Feature activation+2.35e+00

Pos logit contributions
LLOW+0.325
tten+0.317
��+0.308
 Swordsman+0.300
FACE+0.296
Neg logit contributions
ippers-0.310
ipper-0.301
lems-0.243
rones-0.242
 Carney-0.237
Token happens
Token ID4325
Feature activation+1.84e+00

Pos logit contributions
LLOW+1.882
tten+1.836
��+1.797
 Swordsman+1.739
FACE+1.727
Neg logit contributions
ippers-1.622
ipper-1.588
rones-1.258
lems-1.251
lihood-1.246
Token from
Token ID422
Feature activation+1.16e+00

Pos logit contributions
LLOW+1.428
tten+1.393
��+1.355
 Swordsman+1.330
FACE+1.310
Neg logit contributions
ippers-1.336
ipper-1.300
 Carney-1.032
rones-1.031
lems-1.028
Token Monday
Token ID3321
Feature activation+4.51e-01

Pos logit contributions
LLOW+0.864
tten+0.847
��+0.818
 Swordsman+0.800
FACE+0.782
Neg logit contributions
ippers-0.889
ipper-0.867
lems-0.699
rones-0.697
lihood-0.692
Token April
Token ID3035
Feature activation-4.83e+00

Pos logit contributions
LLOW+0.332
tten+0.323
��+0.314
 Swordsman+0.305
FACE+0.301
Neg logit contributions
ippers-0.349
ipper-0.340
rones-0.275
lems-0.274
lihood-0.273
Token 30
Token ID1542
Feature activation-4.58e-01

Pos logit contributions
ippers+3.522
ipper+3.459
rones+2.758
 Carney+2.758
lems+2.748
Neg logit contributions
LLOW-3.692
tten-3.631
��-3.616
ADRA-3.455
 Swordsman-3.404
Tokenth
Token ID400
Feature activation-1.04e+00

Pos logit contributions
ippers+0.274
ipper+0.266
rones+0.200
lems+0.199
 Carney+0.197
Neg logit contributions
LLOW-0.418
tten-0.409
��-0.401
 Swordsman-0.391
FACE-0.387
Token at
Token ID379
Feature activation+8.09e-01

Pos logit contributions
ippers+0.761
ipper+0.743
rones+0.593
lems+0.590
 Carney+0.584
Neg logit contributions
LLOW-0.813
tten-0.794
��-0.779
 Swordsman-0.752
ADRA-0.745
Token 1900
Token ID21489
Feature activation-1.14e+00

Pos logit contributions
LLOW+0.588
tten+0.574
��+0.552
 Swordsman+0.543
FACE+0.531
Neg logit contributions
ippers-0.636
ipper-0.621
rones-0.504
lihood-0.502
lems-0.500
Token g
Token ID308
Feature activation-2.57e+00

Pos logit contributions
ippers+0.993
ipper+0.974
rones+0.809
lems+0.807
 Carney+0.801
Neg logit contributions
LLOW-0.726
tten-0.705
��-0.688
 Swordsman-0.660
ADRA-0.652
Token able
Token ID1498
Feature activation-1.40e+00

Pos logit contributions
ippers+0.033
ipper+0.032
rones+0.026
lems+0.025
mast+0.025
Neg logit contributions
LLOW-0.037
tten-0.037
��-0.035
 Swordsman-0.034
FACE-0.034
Token to
Token ID284
Feature activation-6.13e-01

Pos logit contributions
ippers+1.094
ipper+1.073
lems+0.867
rones+0.867
 Carney+0.858
Neg logit contributions
LLOW-1.021
tten-0.986
��-0.972
ADRA-0.934
 Swordsman-0.933
Token prevent
Token ID2948
Feature activation-4.04e-01

Pos logit contributions
ippers+0.451
ipper+0.441
rones+0.357
lems+0.354
 Carney+0.348
Neg logit contributions
LLOW-0.471
tten-0.467
��-0.448
 Swordsman-0.438
FACE-0.431
Token the
Token ID262
Feature activation-1.89e-01

Pos logit contributions
ippers+0.284
ipper+0.277
rones+0.220
lems+0.218
mast+0.214
Neg logit contributions
LLOW-0.325
tten-0.319
��-0.311
 Swordsman-0.302
FACE-0.298
Token Petro
Token ID36863
Feature activation+4.39e-01

Pos logit contributions
ippers+0.129
ipper+0.126
rones+0.100
lems+0.099
mast+0.098
Neg logit contributions
LLOW-0.155
tten-0.151
��-0.148
 Swordsman-0.144
ADRA-0.141
Tokencar
Token ID7718
Feature activation-4.12e+00

Pos logit contributions
LLOW+0.427
tten+0.422
��+0.410
 Swordsman+0.400
FACE+0.400
Neg logit contributions
ippers-0.233
ipper-0.226
rones-0.161
lihood-0.161
lems-0.160
Tokenibe
Token ID32438
Feature activation-1.82e+00

Pos logit contributions
ippers+1.300
ipper+1.232
rones+0.626
lems+0.623
 Carney+0.597
Neg logit contributions
LLOW-4.952
tten-4.858
��-4.813
 Swordsman-4.689
ADRA-4.676
Token deal
Token ID1730
Feature activation-7.02e-01

Pos logit contributions
ippers+1.012
ipper+0.980
rones+0.719
lems+0.715
 Carney+0.704
Neg logit contributions
LLOW-1.742
tten-1.711
��-1.679
 Swordsman-1.637
ADRA-1.622
Token for
Token ID329
Feature activation+8.86e-01

Pos logit contributions
ippers+0.600
ipper+0.588
rones+0.487
lems+0.486
 Carney+0.481
Neg logit contributions
LLOW-0.460
tten-0.447
��-0.435
 Swordsman-0.418
FACE-0.413
Token two
Token ID734
Feature activation+5.51e-01

Pos logit contributions
LLOW+0.642
tten+0.631
��+0.609
 Swordsman+0.590
FACE+0.585
Neg logit contributions
ippers-0.690
ipper-0.676
rones-0.553
lems-0.547
mast-0.542
Token years
Token ID812
Feature activation+1.88e+00

Pos logit contributions
LLOW+0.365
tten+0.355
��+0.346
 Swordsman+0.333
ADRA+0.329
Neg logit contributions
ippers-0.466
ipper-0.457
rones-0.378
lems-0.375
mast-0.372
Token executions
Token ID30632
Feature activation-2.65e+00

Pos logit contributions
LLOW+0.621
tten+0.608
��+0.592
 Swordsman+0.578
FACE+0.567
Neg logit contributions
ippers-0.613
ipper-0.599
rones-0.480
lems-0.479
lihood-0.472
Token took
Token ID1718
Feature activation+2.23e+00

Pos logit contributions
ippers+1.835
ipper+1.786
rones+1.407
lems+1.388
 Carney+1.387
Neg logit contributions
LLOW-2.162
tten-2.110
��-2.079
 Swordsman-2.007
ADRA-1.991
Token place
Token ID1295
Feature activation+1.74e+00

Pos logit contributions
LLOW+1.443
tten+1.402
��+1.364
 Swordsman+1.313
FACE+1.294
Neg logit contributions
ippers-1.923
ipper-1.887
rones-1.564
lems-1.562
 Carney-1.545
Token on
Token ID319
Feature activation-2.02e-02

Pos logit contributions
LLOW+1.350
tten+1.317
��+1.285
 Swordsman+1.262
FACE+1.235
Neg logit contributions
ippers-1.267
ipper-1.242
lems-0.979
rones-0.979
 Carney-0.964
Token Sunday
Token ID3502
Feature activation-1.48e+00

Pos logit contributions
ippers+0.016
ipper+0.016
rones+0.013
lems+0.013
 Carney+0.013
Neg logit contributions
LLOW-0.014
tten-0.014
��-0.014
 Swordsman-0.013
FACE-0.013
Token November
Token ID3389
Feature activation-4.14e+00

Pos logit contributions
ippers+1.046
ipper+1.019
rones+0.811
lems+0.806
 Carney+0.801
Neg logit contributions
LLOW-1.185
tten-1.156
��-1.137
 Swordsman-1.094
ADRA-1.093
Token 3
Token ID513
Feature activation-7.66e-01

Pos logit contributions
ippers+3.069
ipper+3.003
rones+2.412
 Carney+2.404
lems+2.398
Neg logit contributions
LLOW-3.158
tten-3.090
��-3.064
ADRA-2.929
 Swordsman-2.901
Token,
Token ID11
Feature activation+1.19e-01

Pos logit contributions
ippers+0.535
ipper+0.522
rones+0.413
lems+0.410
 Carney+0.406
Neg logit contributions
LLOW-0.622
tten-0.607
��-0.596
 Swordsman-0.576
ADRA-0.572
Token a
Token ID257
Feature activation-3.70e-01

Pos logit contributions
LLOW+0.092
tten+0.090
��+0.088
 Swordsman+0.085
FACE+0.084
Neg logit contributions
ippers-0.087
ipper-0.085
rones-0.068
lems-0.067
 Carney-0.067
Token source
Token ID2723
Feature activation+1.80e-01

Pos logit contributions
ippers+0.329
ipper+0.322
rones+0.269
lems+0.269
 Carney+0.265
Neg logit contributions
LLOW-0.231
tten-0.224
��-0.218
 Swordsman-0.210
FACE-0.207
Token told
Token ID1297
Feature activation+1.76e+00

Pos logit contributions
LLOW+0.130
tten+0.127
��+0.124
 Swordsman+0.120
FACE+0.118
Neg logit contributions
ippers-0.141
ipper-0.137
rones-0.112
lems-0.112
 Carney-0.110
Token of
Token ID286
Feature activation-2.93e-01

Pos logit contributions
ippers+0.992
ipper+0.968
rones+0.767
lems+0.765
 Carney+0.756
Neg logit contributions
LLOW-1.109
tten-1.083
��-1.061
 Swordsman-1.027
ADRA-1.016
Token his
Token ID465
Feature activation+9.32e-01

Pos logit contributions
ippers+0.202
ipper+0.196
lems+0.157
rones+0.156
ploy+0.152
Neg logit contributions
LLOW-0.239
tten-0.235
��-0.228
 Swordsman-0.223
FACE-0.221
Token ret
Token ID1005
Feature activation+9.60e-01

Pos logit contributions
LLOW+0.813
tten+0.795
��+0.771
 Swordsman+0.760
FACE+0.757
Neg logit contributions
ippers-0.590
ipper-0.567
lems-0.442
rones-0.437
ploy-0.431
Tokenraction
Token ID7861
Feature activation-3.07e-01

Pos logit contributions
LLOW+0.757
tten+0.748
��+0.722
 Swordsman+0.705
FACE+0.694
Neg logit contributions
ippers-0.675
ipper-0.658
lems-0.526
 Carney-0.523
rones-0.522
Token and
Token ID290
Feature activation+2.75e-01

Pos logit contributions
ippers+0.233
ipper+0.228
rones+0.183
lems+0.183
 Carney+0.180
Neg logit contributions
LLOW-0.230
tten-0.225
��-0.219
 Swordsman-0.213
FACE-0.210
Token silence
Token ID9550
Feature activation-4.12e+00

Pos logit contributions
LLOW+0.212
tten+0.207
��+0.202
 Swordsman+0.196
FACE+0.194
Neg logit contributions
ippers-0.203
ipper-0.197
lems-0.160
rones-0.158
ploy-0.155
Token.
Token ID13
Feature activation+3.27e-01

Pos logit contributions
ippers+2.957
ipper+2.883
rones+2.307
 Carney+2.301
lems+2.283
Neg logit contributions
LLOW-3.243
tten-3.175
��-3.105
ADRA-3.026
 Swordsman-2.983
Token This
Token ID770
Feature activation-4.61e-01

Pos logit contributions
LLOW+0.253
tten+0.243
��+0.237
 Swordsman+0.236
FACE+0.232
Neg logit contributions
ippers-0.243
ipper-0.237
lems-0.189
rones-0.188
ploy-0.185
Token year
Token ID614
Feature activation+1.52e+00

Pos logit contributions
ippers+0.363
ipper+0.354
lems+0.291
rones+0.288
ploy+0.282
Neg logit contributions
LLOW-0.334
tten-0.326
��-0.315
 Swordsman-0.308
FACE-0.304
Token,
Token ID11
Feature activation-7.19e-01

Pos logit contributions
LLOW+1.140
tten+1.112
��+1.080
 Swordsman+1.055
FACE+1.039
Neg logit contributions
ippers-1.136
ipper-1.112
lems-0.904
rones-0.891
lihood-0.878
Token on
Token ID319
Feature activation+5.54e-01

Pos logit contributions
ippers+0.536
ipper+0.523
lems+0.420
rones+0.420
lihood+0.413
Neg logit contributions
LLOW-0.550
tten-0.535
��-0.522
 Swordsman-0.509
FACE-0.501